dyoshikawa/rulesync

- Extract the PR number from the argument - Examples: `123`, `#123`, `https://github.com/owner/repo/pull/123`

- Examples: `123`, `#123`, `https://github.com/owner/repo/pull/123`

- A number/URL (`123`, `#123`, `https://github.com/owner/repo/pull/123`) → use it.

2. For each worktree branch that is NOT the default branch (e.g. main), run `git gtr rm --force {branch}` to remove it.

Key findings from the web research that shape the proposal. Keep it tight, but every non-trivial factual claim must be backed by an inline link to its source (e.g., `[official docs](https://...)`). Include exact version numbers where releva

- List every URL consulted during research that materially shaped the proposal, not just the top one or two. Err on the side of including more. - Use full, clickable URLs (e.g., `https://example.com/docs/foo`). Do not shorten, redirect, or 

- Use full, clickable URLs (e.g., `https://example.com/docs/foo`). Do not shorten, redirect, or paraphrase the link target.

- Annotate each entry with a short description so the reader understands _why_ it is cited (e.g., `- https://example.com/docs/foo — official schema reference for the `foo` config`).

- Which features / directories / schemas exist here and will need to map to the target's concepts? - Prefer targeted symbol and search tools over reading whole files. - If the proposal includes popularity / adoption claims, verify the numbe

- If the proposal includes popularity / adoption claims, verify the numbers before writing them down. For npm downloads: `curl -s "https://api.npmjs.org/downloads/point/<start>:<end>/<package>"`. For stars/forks: `gh repo view <owner/repo> 

- Suggested title    - Auto-applied labels (from template frontmatter, if any)    - A pre-filled new-issue URL of the form `https://github.com/<owner>/<repo>/issues/new?template=<template-filename>` when a template exists, otherwise `https:

- Auto-applied labels (from template frontmatter, if any)    - A pre-filled new-issue URL of the form `https://github.com/<owner>/<repo>/issues/new?template=<template-filename>` when a template exists, otherwise `https://github.com/<owner>/

- A pre-filled new-issue URL of the form `https://github.com/<owner>/<repo>/issues/new?template=<template-filename>` when a template exists, otherwise `https://github.com/<owner>/<repo>/issues/new`

the user's request にリリースバージョン（例: `v6.5.0`）またはGitHubリリースURL（例: `https://github.com/dyoshikawa/rulesync/releases/tag/v6.5.0`）が渡される。複数のリリースが渡される場合もある（その場合は1つのXポストにまとめる）。

git gtr rm feature-branch

git gtr rm feature-branch

[Credential-related source omitted]

git gtr rm feature-auth

git gtr rm feature-api

git gtr rm bugfix-login

git gtr rm review-pr-123

git gtr rm hotfix-critical

If it exists, remove it first: `git gtr rm <branch>`

- **"refusing to fetch into branch checked out at..."**: A worktree with that branch exists. `git gtr rm <branch>` first.

rm -f ./tmp/SHA256SUMS

any of them. A deleted fork returns `null` for `headRepository` and `headRepositoryOwner`, and `jq -r` prints that as text — which would make Step 5 push to `https://github.com/null/null.git`. Stop and report instead.

push to `https://github.com/null/null.git`. Stop and report instead.

PR_JSON="$(git rev-parse --git-dir)/merge-pr-<pr_number>/pr.json" git push \   "https://github.com/$(jq -r .headRepositoryOwner.login "$PR_JSON")/$(jq -r .headRepository.name "$PR_JSON").git" \

git push    "https://github.com/$(jq -r .headRepositoryOwner.login "$PR_JSON")/$(jq -r .headRepository.name "$PR_JSON").git"

"https://github.com/$(jq -r .headRepositoryOwner.login "$PR_JSON")/$(jq -r .headRepository.name "$PR_JSON").git" \

rm -rf "$(git rev-parse --git-dir)/merge-pr-<pr_number>"

- Extract the PR number from the argument - Examples: `123`, `#123`, `https://github.com/owner/repo/pull/123`

- Examples: `123`, `#123`, `https://github.com/owner/repo/pull/123`

- OpenCode must be installed.   - If not installed, tell the user it can be installed with `curl -fsSL https://opencode.ai/install | bash`.

- If not installed, tell the user it can be installed with `curl -fsSL https://opencode.ai/install | bash`.

- If not installed, tell the user it can be installed with `curl -fsSL https://opencode.ai/install | bash`.

- https://opencode.ai/docs/ja

Bash(playwright-cli:*) Bash(npx:*) Bash(npm:*)

playwright-cli open # navigate to a page playwright-cli goto https://playwright.dev

# navigate to a page playwright-cli goto https://playwright.dev # interact with the page using refs from the snapshot

playwright-cli goto https://playwright.dev

playwright-cli open # open and navigate right away playwright-cli open https://example.com/

# open and navigate right away playwright-cli open https://example.com/ playwright-cli goto https://playwright.dev

playwright-cli open https://example.com/

playwright-cli goto https://playwright.dev

playwright-cli eval "document.title"

playwright-cli eval "el => el.textContent" e5

playwright-cli eval "el => el.id" e5

playwright-cli eval "el => el.getAttribute('data-testid')" e5

playwright-cli tab-list playwright-cli tab-new playwright-cli tab-new https://example.com/page

playwright-cli tab-new playwright-cli tab-new https://example.com/page playwright-cli tab-close

playwright-cli tab-new https://example.com/page

playwright-cli route "**/*.jpg" --status=404 playwright-cli route "https://api.example.com/**" --body='{"mock": true}'

playwright-cli route "https://api.example.com/**" --body='{"mock": true}'

playwright-cli --raw eval "JSON.stringify(performance.timing)" | jq '.loadEventEnd - .navigationStart'

playwright-cli --raw eval "JSON.stringify([...document.querySelectorAll('a')].map(a => a.href))" > links.json

# Connect to a running browser via CDP endpoint playwright-cli attach --cdp=http://localhost:9222

playwright-cli attach --cdp=http://localhost:9222

> playwright-cli goto https://example.com

### Page - Page URL: https://example.com/ - Page Title: Example Domain

- Page URL: https://example.com/

playwright-cli open https://example.com/form

playwright-cli open https://example.com

playwright-cli tab-new https://example.com/other

playwright-cli open https://example.com

playwright-cli open https://example.com

playwright-cli open https://example.com

playwright-cli eval "el => el.id" e7

playwright-cli eval "el => el.className" e7

playwright-cli eval "el => el.getAttribute('data-testid')" e7

playwright-cli eval "el => el.getAttribute('aria-label')" e7

playwright-cli eval "el => getComputedStyle(el).display" e7

playwright-cli run-code "async page => {   await page.route('**/api/user', async route => {     const response = await route.fetch();

await page.route('**/api/user', async route => {     const response = await route.fetch();     const json = await response.json();

const response = await route.fetch();

playwright-cli run-code "async page => {   await page.context().grantPermissions(['clipboard-read'], {     origin: 'https://example.com'

await page.context().grantPermissions(['clipboard-read'], {     origin: 'https://example.com'   });

origin: 'https://example.com'

# Login and save state playwright-cli run-code "async page => {   await page.goto('https://example.com/login');

playwright-cli run-code "async page => {   await page.goto('https://example.com/login');   await page.getByRole('textbox', { name: 'Email' }).fill('user@example.com');

await page.goto('https://example.com/login');

const results = [];   for (let i = 1; i <= 3; i++) {     await page.goto(\`https://example.com/page/\${i}\`);

for (let i = 1; i <= 3; i++) {     await page.goto(\`https://example.com/page/\${i}\`);     const items = await page.locator('.item').allTextContents();

await page.goto(\`https://example.com/page/\${i}\`);

# Browser 1: Authentication flow playwright-cli -s=auth open https://app.example.com/login

playwright-cli -s=auth open https://app.example.com/login

[Credential-related source omitted]

[Credential-related source omitted]

playwright-cli -s=public open https://example.com

# Start all browsers playwright-cli -s=site1 open https://site1.com &

playwright-cli -s=site1 open https://site1.com &

playwright-cli -s=site2 open https://site2.com &

playwright-cli -s=site3 open https://site3.com &

# Test different user experiences playwright-cli -s=variant-a open "https://app.com?variant=a"

playwright-cli -s=variant-a open "https://app.com?variant=a"

playwright-cli -s=variant-b open "https://app.com?variant=b"

# Use persistent profile (auto-generated location) playwright-cli open https://example.com --persistent

playwright-cli open https://example.com --persistent

# Use persistent profile with custom directory playwright-cli open https://example.com --profile=/path/to/profile

playwright-cli open https://example.com --profile=/path/to/profile

playwright-cli attach --cdp=http://localhost:9222

# These use the same default browser session playwright-cli open https://example.com

playwright-cli open https://example.com

# Open with config file playwright-cli open https://example.com --config=.playwright/my-cli.json

playwright-cli open https://example.com --config=.playwright/my-cli.json

# Open with specific browser playwright-cli open https://example.com --browser=firefox

playwright-cli open https://example.com --browser=firefox

# Open in headed mode playwright-cli open https://example.com --headed

playwright-cli open https://example.com --headed

# Open with persistent profile playwright-cli open https://example.com --persistent

playwright-cli open https://example.com --persistent

# GOOD: Clear purpose playwright-cli -s=github-auth open https://github.com

playwright-cli -s=github-auth open https://github.com

playwright-cli -s=docs-scrape open https://docs.example.com

# AVOID: Generic names playwright-cli -s=s1 open https://github.com

playwright-cli -s=s1 open https://github.com

test("seed", async ({ page }) => {   await page.goto("https://example.com/");

await page.goto("https://example.com/");

export const test = baseTest.extend({   page: async ({ page }, use) => {     await page.goto("https://example.com/");

page: async ({ page }, use) => {     await page.goto("https://example.com/");     await use(page);

await page.goto("https://example.com/");

playwright-cli eval "location.href"     # read URL / state

[Credential-related source omitted]

# Reload page to apply cookies playwright-cli open https://example.com

playwright-cli open https://example.com

"origins": [     {       "origin": "https://example.com",

{       "origin": "https://example.com",       "localStorage": [

"origin": "https://example.com",

# Step 1: Login and save state playwright-cli open https://app.example.com/login

playwright-cli open https://app.example.com/login

# Step 2: Later, restore state and skip login playwright-cli state-load auth.json playwright-cli open https://app.example.com/dashboard

playwright-cli state-load auth.json playwright-cli open https://app.example.com/dashboard # Already logged in!

playwright-cli open https://app.example.com/dashboard

# Set up authentication state playwright-cli open https://example.com

playwright-cli open https://example.com

playwright-cli eval "() => { document.cookie = 'session=abc123'; localStorage.setItem('user', 'john'); }"

# Restore state playwright-cli state-load my-session.json playwright-cli open https://example.com

playwright-cli state-load my-session.json playwright-cli open https://example.com # Cookies and localStorage are restored!

playwright-cli open https://example.com

# Start a session playwright-cli open https://example.com/login

playwright-cli open https://example.com/login

test("login flow", async ({ page }) => {   // Generated code from playwright-cli session:   await page.goto("https://example.com/login");

// Generated code from playwright-cli session:   await page.goto("https://example.com/login");   await page.getByRole("textbox", { name: "Email" }).fill("user@example.com");

await page.goto("https://example.com/login");

playwright-cli open https://example.com

playwright-cli --raw eval "el => el.textContent" e5

playwright-cli --raw eval "el => el.value" e5

# Perform actions playwright-cli open https://example.com

playwright-cli open https://example.com

playwright-cli tracing-start playwright-cli open https://app.example.com

playwright-cli open https://app.example.com

playwright-cli tracing-start playwright-cli open https://slow-site.com

playwright-cli open https://slow-site.com

playwright-cli open https://app.example.com/checkout

# Trace the entire flow, not just the failing step playwright-cli tracing-start playwright-cli open https://example.com

playwright-cli tracing-start playwright-cli open https://example.com # ... all steps leading to the issue ...

playwright-cli open https://example.com

find .playwright-cli/traces -mtime +7 -delete

# Navigate and perform actions playwright-cli goto https://example.com

playwright-cli goto https://example.com

async (page) => {   await page.screencast.start({ path: "video.webm", size: { width: 1280, height: 800 } });   await page.goto("https://demo.playwright.dev/todomvc");

await page.goto("https://demo.playwright.dev/todomvc");

3. Official docs from the selected client map. 4. Re-check sentinel rows through official docs/site, then web search if needed;    confirm candidate URLs with Curl or Fetch. Recognized sentinel phrases:

4. Re-check sentinel rows through official docs/site, then web search if needed;    confirm candidate URLs with Curl or Fetch. Recognized sentinel phrases:    - `No dedicated upstream <feature> surface in map` — upstream has no

confirm candidate URLs with Curl or Fetch. Recognized sentinel phrases:

| Feature       | Official docs                                                                                                    | Upstream surface                                                                                           

| ------------- | ---------------------------------------------------------------------------------------------------------------- | -----------------------------------------------------------------------------------------------------------

| index         | `https://antigravity.google/docs/getting-started`                                                                | Antigravity 2.0, CLI, IDE, and SDK doc trees under one nav (`/docs` redirects here)                        

| `rules`       | `https://antigravity.google/docs/rules`                                                                          | Workspace rules in `.agents/rules/*.md` (legacy `.agent/rules` still read), each **requiring** a valid `tri

| `ignore`      | No dedicated upstream ignore surface in map                                                                      | No ignore page in the Antigravity docs tree; the CLI inherits the Gemini-CLI lineage's project-root `.gemin

| `mcp`         | `https://antigravity.google/docs/mcp`                                                                            | `mcp_config.json`: global `~/.gemini/config/mcp_config.json`, workspace `.agents/mcp_config.json`; IDE also

| `commands`    | `https://antigravity.google/docs/ide/workflows`, `https://antigravity.google/docs/migration/workflows-to-skills` | Workflows (`/workflow-name`, 12,000-character limit per file) are **deprecated and retire on 2026-11-01**; 

| `subagents`   | `https://antigravity.google/docs/subagents`                                                                      | Custom subagents as `.md` + YAML frontmatter: workspace `.agents/agents/<name>.md` or `.agents/agents/<name

| `skills`      | `https://antigravity.google/docs/skills`                                                                         | Agent Skills (`SKILL.md` per folder): workspace `.agents/skills/<skill>/`, global `~/.gemini/config/skills/

| `hooks`       | `https://antigravity.google/docs/hooks`                                                                          | `hooks.json` in the customization dir (`.agents/` or `~/.gemini/config/`), keyed by hook-group name then Pa

| plugins       | `https://antigravity.google/docs/plugins`                                                                        | `plugin.json` (`name` required for the CLI, strict schema), `mcp_config.json`, `hooks.json`, `skills/`, `ag

| `permissions` | `https://antigravity.google/docs/permissions`, `https://antigravity.google/docs/settings`                        | Three access lists — Allow / Ask / Deny — of `action(target)` entries over `read_file`, `write_file`, `read

so generation merges into it instead of overwriting; check the per-surface rows before assuming a dimension owns its own file. `settings.json` is JSON with Comments per `https://docs.augmentcode.com/cli/config` (comments and trailing

before assuming a dimension owns its own file. `settings.json` is JSON with Comments per `https://docs.augmentcode.com/cli/config` (comments and trailing commas), and the adapters parse it as JSONC and patch owned keys in place. Auggie also

Comments per `https://docs.augmentcode.com/cli/config` (comments and trailing

| Feature       | Official docs                                                      | Upstream surface                                                                                                                                         

| ------------- | ------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------

| index         | `https://docs.augmentcode.com/`                                    | Augment documentation index                                                                                                                              

| `rules`       | `https://docs.augmentcode.com/cli/rules`                           | `.augment/rules`, `~/.augment/rules`, AGENTS.md and CLAUDE.md hierarchical rules                                                                         

| `ignore`      | `https://docs.augmentcode.com/cli/setup-auggie/workspace-indexing` | `.augmentignore`, `.gitignore` interaction, workspace indexing filters                                                                                   

| `mcp`         | `https://docs.augmentcode.com/cli/integrations`                    | `mcpServers` inside `settings.json` (there is no `.augment/mcp.json`); the docs show only `~/.augment/settings.json`, plus the transient `--mcp-config` o

| `commands`    | `https://docs.augmentcode.com/cli/custom-commands`                 | `.augment/commands/*.md` (workspace), `~/.augment/commands/*.md` (user); Markdown with optional frontmatter. Also resolved over `.claude/commands` and `.

| `subagents`   | `https://docs.augmentcode.com/cli/subagents`                       | `.augment/agents/*.md` (workspace) and `~/.augment/agents/*.md` (user); YAML frontmatter `name` (required), `description`, `color`, `model`, `tools`, `di

| `skills`      | `https://docs.augmentcode.com/cli/skills`                          | agentskills.io `<name>/SKILL.md` bundles under `.augment/skills/`, `.claude/skills/`, `.agents/skills/` and their `~` equivalents; `name` (1–64 chars, lo

| `hooks`       | `https://docs.augmentcode.com/cli/hooks`                           | A `hooks` block in the layered `settings.json` (`/etc/augment/` or `%ProgramData%\Augment\`, `<workspace>/.augment/settings.local.json`, `<workspace>/.au

| `permissions` | `https://docs.augmentcode.com/cli/permissions`                     | `toolPermissions` in `settings.json` at either scope; `allow`/`deny`/`ask-user`, first-match-wins rules                                                  

| `checks`      | `https://docs.augmentcode.com/codereview/review-guidelines`        | `<repo-root>/.augment/code_review_guidelines.yaml` — project scope only; top-level `areas` (each with `description`, `globs`, `rules[{id, description, se

| `plugins`     | `https://docs.augmentcode.com/cli/plugins`                         | Plugin bundles (`.augment-plugin/plugin.json`, `.augment-plugin/marketplace.json`, `commands/`, `agents/`, `rules/`, `skills/`, `hooks/hooks.json`, `.mcp

| Feature       | Official docs                                              | Upstream surface                                             | | ------------- | ---------------------------------------------------------- | -------------------

| ------------- | ---------------------------------------------------------- | ------------------------------------------------------------ | | index         | `https://code.claude.com/docs/llms.txt`                    | Docs index         

| index         | `https://code.claude.com/docs/llms.txt`                    | Docs index                                                   |

| `rules`       | `https://code.claude.com/docs/en/memory`                   | `CLAUDE.md`, project memory, imports, discovery, precedence  |

| `ignore`      | `https://code.claude.com/docs/en/permissions`              | `permissions.deny` read rules in Claude settings             |

| `mcp`         | `https://code.claude.com/docs/en/mcp`                      | MCP scopes, transports, CLI-managed servers                  |

| `commands`    | `https://code.claude.com/docs/en/agent-sdk/slash-commands` | `.claude/commands/<name>.md`, metadata, arguments            |

| `subagents`   | `https://code.claude.com/docs/en/sub-agents`               | `.claude/agents/<name>.md`, fields, tool selection           |

| `skills`      | `https://code.claude.com/docs/en/skills`                   | `.claude/skills/<name>/SKILL.md`, metadata, supporting files |

| `hooks`       | `https://code.claude.com/docs/en/hooks`                    | Hook events, matchers, and `.claude/settings.json` commands  |

| `permissions` | `https://code.claude.com/docs/en/permissions`              | Permission rules and settings behavior                       |

| Feature       | Official docs                                               | Upstream surface                                                                 | | ------------- | -----------------------------------------------------------

| ------------- | ----------------------------------------------------------- | -------------------------------------------------------------------------------- | | index         | `https://docs.cline.bot/`                                  

| index         | `https://docs.cline.bot/`                                   | Cline documentation index                                                        |

| `rules`       | `https://docs.cline.bot/customization/cline-rules`          | Rules, workflows, `.clinerules`, and customization surfaces                      |

| `ignore`      | `https://docs.cline.bot/customization/clineignore`          | `.clineignore` customization surface                                             |

| `mcp`         | `https://docs.cline.bot/mcp/adding-and-configuring-servers` | `cline_mcp_settings.json`, stdio/HTTP/SSE style MCP server entries               |

| `commands`    | `https://docs.cline.bot/core-workflows/using-commands`      | Slash commands and workflow-style reusable commands                              |

| `subagents`   | No dedicated upstream subagents surface in map              | No Rulesync-supported Cline subagents target in map                              | | `skills`      | `https://docs.cline.bot/customization/skills`              

| `skills`      | `https://docs.cline.bot/customization/skills`               | `.cline/skills`, `~/.cline/skills`, `.clinerules/skills`, `.claude/skills`       |

| `hooks`       | `https://docs.cline.bot/cline-cli/configuration`            | CLI configuration exposes a Hooks tab                                            |

| `permissions` | `https://docs.cline.bot/features/auto-approve`              | Auto approve settings for read, edit, commands, browser, MCP, and request limits |

| Feature       | Official docs                                                  | Upstream surface                                             | | ------------- | -------------------------------------------------------------- | -----------

| ------------- | -------------------------------------------------------------- | ------------------------------------------------------------ | | index         | `https://learn.chatgpt.com/docs/llms.txt`                      | Docs index 

| index         | `https://learn.chatgpt.com/docs/llms.txt`                      | Docs index                                                   |

| `rules`       | `https://learn.chatgpt.com/docs/agent-configuration/agents-md` | `AGENTS.md` and override behavior                            |

| `ignore`      | No dedicated upstream ignore surface in map                    | No Rulesync-supported Codex CLI ignore target in map         | | `mcp`         | `https://learn.chatgpt.com/docs/extend/mcp?surface=cli`        | MCP server 

| `mcp`         | `https://learn.chatgpt.com/docs/extend/mcp?surface=cli`        | MCP server config, transports, authentication                |

| `commands`    | `https://learn.chatgpt.com/docs/custom-prompts`                | `~/.codex/prompts/*.md`, metadata, arguments                 |

| `subagents`   | `https://learn.chatgpt.com/docs/agent-configuration/subagents` | Subagent files, fields, model and tool config                |

| `skills`      | `https://learn.chatgpt.com/docs/build-skills`                  | `.agents/skills/<name>/SKILL.md`, metadata, supporting files |

| `hooks`       | `https://learn.chatgpt.com/docs/hooks`                         | Hook events, matcher patterns, hook JSON, feature flags      |

| `permissions` | `https://learn.chatgpt.com/docs/agent-approvals-security`      | Approval policy and sandbox behavior                         |

| `permissions` | `https://learn.chatgpt.com/docs/config-file/config-reference`  | Config keys and profile overrides                            |

| `permissions` | `https://learn.chatgpt.com/docs/agent-configuration/rules`     | Command execution rules files                                |

| Feature       | Official docs                                                                                                     | Upstream surface                                                                                     | | -

| ------------- | ----------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------- | | i

| index         | `https://docs.github.com/en/copilot`                                                                              | GitHub Copilot documentation index                                                                   |

| `rules`       | `https://docs.github.com/en/copilot/how-tos/configure-custom-instructions/add-repository-instructions`            | `.github/copilot-instructions.md`, `.github/instructions/*.instructions.md`, agent instruction files |

| `ignore`      | No dedicated upstream ignore surface in map                                                                       | No Rulesync-supported Copilot ignore target in map                                                   | | `

| `mcp`         | `https://docs.github.com/en/copilot/customizing-copilot/extending-copilot-chat-with-mcp`                          | `.vscode/mcp.json`, MCP server definitions                                                           |

| `commands`    | `https://docs.github.com/en/copilot/concepts/about-customizing-github-copilot-chat-responses`                     | Prompt files such as `.github/prompts/*.prompt.md`                                                   |

| `subagents`   | `https://docs.github.com/en/copilot/concepts/agents/copilot-cli/about-custom-agents`                              | Agent profiles in `.github/agents/*.md`                                                              |

| `skills`      | `https://docs.github.com/en/copilot/how-tos/copilot-on-github/customize-copilot/customize-cloud-agent/add-skills` | Agent skills in `.github/skills/<name>/SKILL.md`                                                     |

| `hooks`       | `https://docs.github.com/en/copilot/concepts/agents/coding-agent/about-hooks`                                     | Repository hooks in `.github/hooks/*.json`                                                           |

| Feature       | Official docs                                                                                           | Upstream surface                                                                                                    

| ------------- | ------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------

| index         | `https://docs.github.com/en/copilot/how-tos/copilot-cli/customize-copilot/overview`                     | Copilot CLI customization overview                                                                                  

| `rules`       | `https://docs.github.com/en/copilot/how-tos/copilot-cli/customize-copilot/add-custom-instructions`      | `.github/copilot-instructions.md`, `.github/instructions/*.instructions.md`, `AGENTS.md`, `CLAUDE.md`, `GEMINI.md`, 

| `ignore`      | No dedicated upstream ignore surface in map                                                             | No Rulesync-supported Copilot CLI ignore target in map                                                              

| `mcp`         | `https://docs.github.com/en/copilot/how-tos/copilot-cli/customize-copilot/add-mcp-servers`              | MCP servers, user `~/.copilot/mcp-config.json`, project MCP config precedence                                       

| `commands`    | No dedicated upstream commands surface in map                                                           | No Rulesync-supported Copilot CLI commands target in map                                                            

| `subagents`   | `https://docs.github.com/en/copilot/how-tos/copilot-cli/customize-copilot/create-custom-agents-for-cli` | Custom agent profiles used as subagents, `.github/agents/*.agent.md`, `~/.copilot/agents/*.agent.md`                

| `skills`      | `https://docs.github.com/en/copilot/how-tos/copilot-cli/customize-copilot/add-skills`                   | Agent skills in `.github/skills`, `.claude/skills`, `.agents/skills`, `~/.copilot/skills`, `~/.agents/skills`       

| `hooks`       | `https://docs.github.com/en/copilot/how-tos/copilot-cli/customize-copilot/use-hooks`                    | `.github/hooks/<name>.json`, hook events, `bash`/`powershell` command entries                                       

| `permissions` | `https://docs.github.com/en/copilot/how-tos/copilot-cli/use-copilot-cli/allowing-tools`                 | Tool allow/deny behavior and interactive approval                                                                   

| Feature       | Official docs                                       | Upstream surface                                                                                   | | ------------- | -------------------------------------------------

| ------------- | --------------------------------------------------- | -------------------------------------------------------------------------------------------------- | | index         | `https://cursor.com/docs/cli/using`              

| index         | `https://cursor.com/docs/cli/using`                 | Cursor CLI overview, rules, MCP, command approval, non-interactive mode                            |

| `rules`       | `https://cursor.com/docs/rules`                     | `.cursor/rules/*.mdc`, User Rules, `AGENTS.md`, `.cursorrules` legacy                              |

| `ignore`      | `https://cursor.com/docs/reference/ignore-file`     | `.cursorignore` and global ignore settings                                                         |

| `mcp`         | `https://cursor.com/docs/cli/mcp`                   | Cursor CLI MCP, shared `mcp.json` configuration, project/global/nested precedence                  |

| `commands`    | `https://cursor.com/help/customization/skills`      | Cursor has merged reusable command-like workflows into Skills; Rulesync still maps command files   |

| `subagents`   | `https://cursor.com/docs/plugins`                   | Plugin-bundled agents/subagents and marketplace surfaces                                           |

| `skills`      | `https://cursor.com/docs/plugins`                   | Plugin-bundled skills and marketplace surfaces                                                     |

| `hooks`       | `https://cursor.com/docs/hooks`                     | `.cursor/hooks.json`, hook events, command/prompt hook entries                                     |

| `permissions` | `https://cursor.com/docs/cli/reference/permissions` | `.cursor/cli.json`, `~/.cursor/cli-config.json`, `Shell`, `Read`, `Write`, `WebFetch`, `Mcp` rules |

| Feature       | Official docs                                                      | Upstream surface                                                                                                                                         

| ------------- | ------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------

| index         | `https://docs.langchain.com/oss/deepagents/code/overview`          | Deep Agents CLI overview                                                                                                                                 

| `rules`       | `https://docs.langchain.com/oss/deepagents/code/overview`          | AGENTS.md files, memory, persistent project context                                                                                                      

| `ignore`      | No dedicated upstream ignore surface in map                        | No Rulesync-supported Deep Agents ignore target in map                                                                                                   

| `mcp`         | `https://docs.langchain.com/oss/deepagents/code/overview`          | MCP tools surfaced through CLI configuration                                                                                                             

| `commands`    | No dedicated upstream commands surface in map                      | No Rulesync-supported Deep Agents commands target in map                                                                                                 

| `subagents`   | `https://docs.langchain.com/oss/deepagents/code/overview`          | `task` delegation to subagents                                                                                                                           

| `skills`      | `https://docs.langchain.com/oss/deepagents/code/memory-and-skills` | `.deepagents/skills`, `.agents/skills`, `~/.deepagents/<agent>/skills` (`<agent>` defaults to `agent`), progressive skill loading                        

| `hooks`       | `https://docs.langchain.com/oss/deepagents/code/hooks`             | Hooks v2 (GA in deepagents-code 0.1.52, 2026-08-04): `{ "hooks": { "<Event>": [ { matcher, hooks } ] } }` in project `.deepagents/hooks.json` (needs work

| `permissions` | `https://docs.langchain.com/oss/deepagents/code/configuration`     | `[shell].allow_list` in the user config `~/.deepagents/config.toml` (global only; no project config file): executable names matched exactly against the f

| `extensions`  | `https://docs.langchain.com/oss/deepagents/code/configuration`     | Python extensions auto-loaded from the user's `~/.deepagents/extensions/` and the project's `<root>/.deepagents/extensions/`, plus the `dcode.extensions`

| Feature       | Official docs                                                     | Upstream surface                                                                                                                           | | -----------

| ------------- | ----------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | | index      

| index         | `https://docs.devin.ai/cli`                                       | Devin Local (Devin CLI) quickstart; extensibility index at `/cli/extensibility` (`/cli/overview` now 404s)                                 |

| `rules`       | `https://docs.devin.ai/cli/extensibility/rules`                   | `.devin/rules/*.md` + root `AGENTS.md`/`AGENTS.local.md` (project), `~/.devin/rules/*.md` + `~/.config/devin/AGENTS.md` (global)           |

| `ignore`      | `https://docs.devin.ai/desktop/context-awareness/windsurf-ignore` | Three project files with no documented precedence: `.devinignore`, `.codeiumignore`, `.windsurfignore`; global `~/.codeium/.codeiumignore` |

| `mcp`         | `https://docs.devin.ai/cli/extensibility/mcp/overview`            | `mcpServers` key in `.devin/config.json` / `~/.config/devin/config.json`                                                                   |

| `commands`    | `https://docs.devin.ai/cli/extensibility/skills/overview`         | No separate commands file surface: a skill IS the slash command (`/skill-name`), and plugin skills are `/<plugin>:<skill>`                 |

| `subagents`   | `https://docs.devin.ai/cli/subagents`                             | Subagent profiles under `.devin/agents/`, global `~/.config/devin/agents/`                                                                 |

| `skills`      | `https://docs.devin.ai/cli/extensibility/skills/overview`         | `<name>/SKILL.md` under `.devin/skills/` (also `.agents/`, `.windsurf/`); global `~/.config/devin/skills/` (also `~/.codeium/<channel>/`)  | | `hooks`    

| `hooks`       | `https://docs.devin.ai/cli/extensibility/hooks/overview`          | Claude-style events, `.devin/hooks.v1.json` / `hooks` key in `config.json`                                                                 |

| `permissions` | `https://docs.devin.ai/cli/reference/permissions`                 | `permissions` block (allow/deny/ask) in `config.json`, `Read/Write/Exec/Fetch`                                                             |

| Feature       | Official docs                                                              | Upstream surface                                                                                                                                 

| ------------- | -------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------

| index         | `https://docs.factory.ai/droid-cli/quickstart`                             | Factory Droid CLI documentation                                                                                                                  

| `rules`       | `https://docs.factory.ai/harness/agents-md`                                | `AGENTS.md` at the repo root, nested `AGENTS.md`, personal `~/.factory/AGENTS.md`, and the separate `DESIGN.md` architecture document            

| `ignore`      | No dedicated upstream ignore surface in map                                | Factory documents no `.droidignore` / `.factoryignore` equivalent; no Rulesync-supported Factory Droid ignore target                             

| `mcp`         | `https://docs.factory.ai/harness/mcp`                                      | `.factory/mcp.json` (project) and `~/.factory/mcp.json` (user); stdio and HTTP servers                                                           

| `commands`    | `https://docs.factory.ai/harness/custom-slash-commands`                    | `.factory/commands/` and `~/.factory/commands/`; `description` and `argument-hint` frontmatter only — "Tool scoping is not available for custom c

| `subagents`   | `https://docs.factory.ai/harness/subagents`                                | Custom droids as `.factory/droids/<name>.md` and `~/.factory/droids/<name>.md`. (`/cli/configuration/custom-droids` and `/harness/custom-droids` 

| `skills`      | `https://docs.factory.ai/harness/skills`                                   | `.factory/skills/<name>/SKILL.md` and `~/.factory/skills/<name>/SKILL.md`; `skill.mdx` supporting files; invocation controls; also discovered at 

| `hooks`       | `https://docs.factory.ai/harness/hooks`                                    | `.factory/hooks.json` and `~/.factory/hooks.json` (legacy `settings.json` fallback); nine events — `PreToolUse`, `PostToolUse`, `UserPromptSubmit

| `permissions` | `https://docs.factory.ai/droid-cli/settings`                               | `settings.json` at either scope: `commandAllowlist` / `commandDenylist` / `commandBlocklist` (deprecated in favor of `permissionRules`, see `http

| `checks`      | `https://docs.factory.ai/software-factory/code-review-ci`                  | `.factory/skills/review-guidelines/SKILL.md` — review guidance delivered as a reserved skill directory rather than its own config file           

| threat model  | `https://docs.factory.ai/software-factory/security-review`                 | `.factory/threat-model.md` — "if `.factory/threat-model.md` exists, Droid uses it as the attack-surface map" for Security Review; documented only

| org settings  | `https://docs.factory.ai/enterprise/hierarchical-settings-and-org-control` | The seven settings levels and the org-delivered `settings.json` keys, including `builtInToolAutonomyOverrides`, `mcpAutonomyUrlOverrides`, `allow

| output styles | `https://docs.factory.ai/droid-cli/output-styles`                          | `.factory/output-styles/<name>.md` and `~/.factory/output-styles/<name>.md`; `.md` only, no nesting; optional `name` / `description` frontmatter;

| `plugins`     | `https://docs.factory.ai/harness/plugins`                                  | Plugin bundles carrying `.factory-plugin/plugin.json` and `.factory-plugin/marketplace.json`, consumed through the `extraKnownMarketplaces` / `en

| Feature       | Official docs                                                                           | Upstream surface                                                                              | | ------------- | ------------------

| ------------- | --------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- | | index         | `https://github.co

| index         | `https://github.com/google-gemini/gemini-cli/blob/main/docs/index.md`                   | Gemini CLI docs index                                                                         |

| `rules`       | `https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/gemini-md.md`           | `GEMINI.md`, context hierarchy, imports, configurable context file names                      |

| `ignore`      | `https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/gemini-ignore.md`       | `.geminiignore`, file filtering settings                                                      |

| `mcp`         | `https://github.com/google-gemini/gemini-cli/blob/main/docs/tools/mcp-server.md`        | `settings.json` `mcpServers`, stdio/SSE/HTTP transports, tool include/exclude settings        |

| `commands`    | `https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/custom-commands.md`     | `.gemini/commands/*.toml`, `description`, `prompt`, `{{args}}`, `!{...}`                      |

| `subagents`   | `https://github.com/google-gemini/gemini-cli/blob/main/docs/core/subagents.md`          | `.gemini/agents/*.md`, YAML frontmatter, tools, MCP, model, run limits                        |

| `skills`      | `https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/skills.md`              | Agent skills management commands, `.gemini/skills`, reload/list/install/enable/disable        |

| `hooks`       | `https://github.com/google-gemini/gemini-cli/blob/main/docs/hooks/writing-hooks.md`     | `.gemini/settings.json` hooks, matcher groups, command hooks, hook-specific JSON output       |

| `permissions` | `https://github.com/google-gemini/gemini-cli/blob/main/docs/reference/configuration.md` | Policy engine, approval modes, `allowed-tools`, `allowed-mcp-server-names`, security settings |

| Feature       | Official docs                                                             | Upstream surface                                                                                                                                  

| ------------- | ------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------

| index         | `https://goose-docs.ai/docs/category/getting-started/`                    | Goose documentation index                                                                                                                         

| `rules`       | `https://goose-docs.ai/docs/guides/context-engineering/using-goosehints/` | `.goosehints`, `AGENTS.md`, nested hints, global `~/.agents/AGENTS.md`                                                                            

| `ignore`      | Retired upstream (docs removed in v1.44.0; goose#10343)                   | No ignore file — `.gitignore` plus tool permissions are the guidance                                                                              

| `mcp`         | `https://goose-docs.ai/docs/getting-started/using-extensions/`            | Global `config.yaml` `extensions:`; project open-plugin `.mcp.json`                                                                               

| `commands`    | `https://goose-docs.ai/docs/guides/recipes/recipe-reference/`             | Recipes at `.goose/recipes/` and `~/.config/goose/recipes/`                                                                                       

| `subagents`   | `https://goose-docs.ai/docs/guides/context-engineering/custom-agents/`    | Custom agents (Markdown), `.goose/agents/` + `~/.config/goose/agents/` et al.                                                                     

| `skills`      | `https://goose-docs.ai/docs/guides/context-engineering/using-skills/`     | `.goose/skills/`, `.agents/skills/`, global `~/.config/goose/skills/`                                                                             

| `hooks`       | `https://goose-docs.ai/docs/guides/context-engineering/hooks/`            | Open Plugins `hooks/hooks.json`; twelve `HookEvent` values on main (2026-09) incl. `PreToolUseResult`; no `SubagentStart`/`SubagentStop`. Rulesync

| `permissions` | `https://goose-docs.ai/docs/guides/managing-tools/tool-permissions/`      | Global `~/.config/goose/permission.yaml` (`user` key) in `goose-permissions.ts`                                                                   

| Feature       | Official docs                                                       | Upstream surface                                                                                                                                        

| ------------- | ------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------

| index         | `https://junie.jetbrains.com/docs/junie-ide-plugin.html`            | Junie IDE plugin and CLI documentation                                                                                                                  

| `rules`       | `https://junie.jetbrains.com/docs/junie-ide-plugin.html`            | `.junie/AGENTS.md` (used exclusively when present), root `AGENTS.md` + `.junie/playbook.md` + `.junie/rules/*.md`, legacy guidelines                    

| `ignore`      | `https://junie.jetbrains.com/docs/junie-ide-plugin.html`            | `.aiignore` restrictions (IDE integration)                                                                                                              

| `mcp`         | `https://junie.jetbrains.com/docs/junie-cli-mcp-configuration.html` | `.junie/mcp/mcp.json`, `~/.junie/mcp/mcp.json`, stdio and remote MCP servers                                                                            

| `commands`    | `https://junie.jetbrains.com/docs/slash-commands.html`              | Custom slash commands and Junie CLI command locations                                                                                                   

| `subagents`   | `https://junie.jetbrains.com/docs/junie-cli-subagents.html`         | `.junie/agents` custom agents plus `.agents/` / `~/.agents/` discovery roots                                                                            

| `skills`      | `https://junie.jetbrains.com/docs/agent-skills.html`                | `.junie/skills` plus the shared `.agents/skills` roots (import-only), and `--skill-location` / `skill-locations` custom folders (out of scope)          

| `hooks`       | `https://junie.jetbrains.com/docs/junie-cli-hooks.html`             | Junie CLI hooks (global `~/.junie/config.json`; project `.junie/config.json` hooks are ignored unless passed via `--config-location`)                   

| `permissions` | `https://junie.jetbrains.com/docs/action-allowlist.html`            | Action Allowlist                                                                                                                                        

| extensions    | `https://junie.jetbrains.com/docs/junie-cli-extensions.html`        | CLI Extensions bundles (native `.junie-extension/marketplace.json` + Claude-compatible `.claude-plugin/marketplace.json`); no dedicated rulesync target 

| Feature       | Official docs                                                          | Upstream surface                                                                                                                                     

| ------------- | ---------------------------------------------------------------------- | -----------------------------------------------------------------------------------------------------------------------------------------------------

| index         | `https://kilo.ai/docs/`                                                | Kilo Code documentation index                                                                                                                        

| `rules`       | `https://kilo.ai/docs/customize/custom-instructions`                   | Custom instructions, `.kilo/rules-*`, `.kilorules-*`, mode-specific instructions                                                                     

| `ignore`      | `https://kilo.ai/docs/customize/context/kilocodeignore`                | `.kilocodeignore` access-control surface, gitignore syntax, workspace root only; Rulesync emits the same name                                        

| `mcp`         | `https://kilo.ai/docs/automate/mcp/using-in-kilo-code`                 | `kilo.jsonc`, `.kilo/kilo.jsonc`, global `~/.config/kilo/kilo.jsonc`, MCP tool permissions                                                           

| `commands`    | `https://kilo.ai/docs/customize/custom-modes`                          | Mode and workflow customization surfaces                                                                                                             

| `subagents`   | `https://kilo.ai/docs/customize/custom-subagents`                      | `.kilo/agents` (project) and `~/.config/kilo/agents` (global); file name is the `@agent` id                                                          

| `skills`      | `https://kilo.ai/docs/customize/skills`                                | `.kilo/skills`, `~/.kilo/skills`, plus `.agents/skills` / `.claude/skills` compatibility roots and `kilo.jsonc` `skills.paths` / `skills.urls`; the p

| `hooks`       | `https://kilo.ai/docs/automate/extending/plugins`                      | Plugin modules auto-registered from `.kilo/plugins` and `~/.config/kilo/plugins`, each also in its singular `plugin/` form (plus the legacy `.kilocod

| `permissions` | `https://kilo.ai/docs/getting-started/settings/auto-approving-actions` | `kilo.jsonc` permission values, `allow`/`ask`/`deny`, built-in and MCP tool permission keys                                                          

| Feature       | Official docs                                         | Upstream surface                                                           | | ------------- | ----------------------------------------------------- | ---------------

| ------------- | ----------------------------------------------------- | -------------------------------------------------------------------------- | | index         | `https://kiro.dev/docs/`                              | Kiro IDE docume

| index         | `https://kiro.dev/docs/`                              | Kiro IDE documentation index                                               |

| `rules`       | `https://kiro.dev/docs/steering/`                     | `.kiro/steering`, global `~/.kiro/steering`, AGENTS.md steering directives |

| `ignore`      | `https://kiro.dev/docs/kiroignore/`                   | `.kiroignore` (project), global `~/.kiro/settings/kiroignore` (`--global`) |

| `mcp`         | `https://kiro.dev/docs/mcp/`                          | MCP server configuration and prompt/resource mentions                      |

| `commands`    | `https://kiro.dev/docs/chat/slash-commands/`          | Slash commands for hooks, steering files, and skill commands               |

| `subagents`   | `https://kiro.dev/docs/cli/reference/slash-commands/` | `/agent` command, `.kiro/agents`, `~/.kiro/agents`                         |

| `skills`      | `https://kiro.dev/docs/skills/`                       | `.kiro/skills`, `~/.kiro/skills`, Agent Skills standard                    |

| `hooks`       | `https://kiro.dev/docs/hooks/`                        | Agent hooks for IDE events and manual triggers                             |

| `permissions` | `https://kiro.dev/docs/cli/reference/slash-commands/` | `/tools` permissions and trusted tools                                     |

| JetBrains ThinkRail (`JetBrains/thinkrail`)   | 2026-10-27 | ThinkRail documents a project config surface of its own (e.g. a `.thinkrail/` tree), or stops delegating to pi; today it is an incubator IDE (stable v0.3.0 2026-10-29, 6,435 sta

| Databricks Genie Code                         | 2026-10-27 | A local CLI/IDE surface reads Genie Code config from a developer's repo, or Databricks documents `.assistant/` as a Git-folder convention with instructions/MCP beside skills; to

| Kun (`KunAgent/Kun`)                          | 2026-10-27 | Official docs pin a file-based project layout (rules / MCP / skills paths); today it is a GUI+TUI workbench (6,327 stars, v0.4.3 2026-10-27, PolyForm NC licence) whose MCP / ski

`https://github.com/Zoo-Code-Org/Zoo-Code` carries an `apps/cli` package

Re-checked 2026-08-17 and still unmet: `apps/cli/package.json` on the default branch is unchanged, and `https://registry.npmjs.org/@roo-code%2Fcli` returns

branch is unchanged, and `https://registry.npmjs.org/@roo-code%2Fcli` returns

- ForgeCode: `https://github.com/tailcallhq/forgecode` (README lists

`AGENTS.md`, `.forge/agents/*.md`, `.forge/commands/*.yaml`, `forge.yaml`,   `.forge/skills/<name>/SKILL.md`, `.mcp.json`),   `https://forgecode.dev/docs/agent-configuration/`.

`.forge/skills/<name>/SKILL.md`, `.mcp.json`),   `https://forgecode.dev/docs/agent-configuration/`. - Verdent: `https://www.verdent.ai/docs/verdent-for-vscode/configuration/settings`.

`https://forgecode.dev/docs/agent-configuration/`.

- Verdent: `https://www.verdent.ai/docs/verdent-for-vscode/configuration/settings`.

- Baidu Comate / Zulu: `https://www.npmjs.com/package/@comate/zulu`,

`https://docs.cloudbase.net/en/ai/cloudbase-ai-toolkit/ide-setup/baidu-comate`

(third-party Tencent CloudBase documentation, not a Baidu primary source; no   official English page for the `.baidu-comate/mcp.json` layout was found). - Warp Factories: `https://docs.warp.dev/factories/factory-as-code/` (recorded

official English page for the `.baidu-comate/mcp.json` layout was found). - Warp Factories: `https://docs.warp.dev/factories/factory-as-code/` (recorded   from the `warp` re-check; the 2026-08-23 comment on #2598 said this entry had

- Warp Factories: `https://docs.warp.dev/factories/factory-as-code/` (recorded

- fx: `https://github.com/vercel-labs/fx`,

`https://fx.sh/docs/configure-fx/configuration`,

`https://fx.sh/docs/configure-fx/permissions`,

`https://fx.sh/docs/capabilities/mcp`, `https://fx.sh/docs/capabilities/skills`.

- Zencoder: `https://docs.zencoder.ai/llms-full.txt` (the rules-file layout is

only described in course material such as   `https://docs.zencoder.ai/learn/10x-engineer/module-03`, not on a reference   page).

`https://docs.zencoder.ai/learn/10x-engineer/module-03`, not on a reference

page). - Nanocoder: `https://github.com/Nano-Collective/nanocoder`,   `https://github.com/Nano-Collective/nanocoder/blob/main/docs/configuration/index.md`.

- Nanocoder: `https://github.com/Nano-Collective/nanocoder`,

`https://github.com/Nano-Collective/nanocoder/blob/main/docs/configuration/index.md`.

- Open Interpreter: `https://github.com/openinterpreter/openinterpreter/blob/main/docs/portability.md`,

`https://github.com/openinterpreter/openinterpreter/blob/main/docs/hooks.md`,

`https://www.openinterpreter.com/docs/terminal/config`.

- MiniMax Code: `https://github.com/MiniMax-AI/minimax-code`,

`https://agent.minimax.io/docs/cli/configuration.md`.

- Prime Agent: `https://github.com/PrimeIntellect-ai/prime-agent`.

- Claurst: `https://github.com/Kuberwastaken/claurst`.

- Kiro Crew: `https://github.com/kirodotdev/KiroCrew`,

`https://github.com/kirodotdev/KiroCrew/blob/main/src/kiro_crew/docs/configuration.md`,

`https://github.com/kirodotdev/KiroCrew/blob/main/src/kiro_crew/docs/steering-and-hooks.md`,

`https://github.com/kirodotdev/KiroCrew/blob/main/src/kiro_crew/docs/skills.md`.

- Kimchi: `https://github.com/getkimchi/kimchi`.

- JetBrains ThinkRail: `https://github.com/JetBrains/thinkrail`.

- Databricks Genie Code:   `https://docs.databricks.com/aws/en/genie-code/skills`. - Kun: `https://github.com/KunAgent/Kun`,

`https://docs.databricks.com/aws/en/genie-code/skills`.

- Kun: `https://github.com/KunAgent/Kun`,

`https://www.kun-agent.com/llms.txt`.

- avante.nvim: `https://github.com/avante-corp/avante.nvim`

(`lua/avante/utils/prompts.lua` for the fallback file list). - FuXi: `https://github.com/fuxicodex/Fuxi`,   `https://github.com/fuxicodex/Fuxi/blob/main/docs/usage.md`.

- FuXi: `https://github.com/fuxicodex/Fuxi`,

`https://github.com/fuxicodex/Fuxi/blob/main/docs/usage.md`.

- OpenCursor: `https://github.com/PawanOsman/OpenCursor`.

- Docker Agent: `https://github.com/docker/docker-agent`.

| Feature       | Official docs                               | Upstream surface                                                                              | | ------------- | ------------------------------------------- | ----------------

| ------------- | ------------------------------------------- | --------------------------------------------------------------------------------------------- | | index         | `https://opencode.ai/docs/`                 | OpenCode docs in

| index         | `https://opencode.ai/docs/`                 | OpenCode docs index                                                                           |

| `rules`       | `https://opencode.ai/docs/rules/`           | `AGENTS.md`, global `~/.config/opencode/AGENTS.md`, Claude Code compatibility, `instructions` |

| `ignore`      | No dedicated upstream ignore surface in map | No Rulesync-supported OpenCode ignore target in map                                           | | `mcp`         | `https://opencode.ai/docs/mcp-servers/`     | `opencode.json` 

| `mcp`         | `https://opencode.ai/docs/mcp-servers/`     | `opencode.json` `mcp`, `local`/`remote` servers, `environment`, `enabled`, tool gates         |

| `commands`    | `https://opencode.ai/docs/commands/`        | `.opencode/commands/*.md`, `~/.config/opencode/commands`, config `command` entries            |

| `subagents`   | `https://opencode.ai/docs/agents/`          | `.opencode/agent/*.md`, `~/.config/opencode/agent`, agent modes, tools, permissions           |

| `skills`      | `https://opencode.ai/docs/skills/`          | `.opencode/skills/<name>/SKILL.md`, compatible `.claude/skills`, `.agents/skills`, metadata   |

| `hooks`       | `https://opencode.ai/docs/plugins/`         | Plugin events such as `session.created`, `tool.execute.before`, `permission.asked`            |

| `permissions` | `https://opencode.ai/docs/permissions`      | `permission` config, `allow`/`ask`/`deny`, granular tool rules, per-agent overrides           |

| Feature       | Official docs                                                                                                                                                                    | Upstream surface                           

| ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------

| index         | `https://pi.dev/docs/latest`                                                                                                                                                     | Pi Coding Agent documentation index        

| `rules`       | `https://pi.dev/docs/latest/usage`                                                                                                                                               | `AGENTS.override.md` (tried first in every 

| `ignore`      | No dedicated upstream ignore surface in map                                                                                                                                      | No Rulesync-supported Pi ignore target in m

| `mcp`         | No dedicated upstream MCP surface in map                                                                                                                                         | No Rulesync-supported Pi MCP target in map 

| `commands`    | `https://pi.dev/docs/latest/prompt-templates`                                                                                                                                    | `.pi/prompts/*.md`, `~/.pi/agent/prompts/*.

| `subagents`   | No dedicated upstream subagents surface in map                                                                                                                                   | No Rulesync-supported Pi subagents target i

| `skills`      | `https://pi.dev/docs/latest/skills`                                                                                                                                              | `.pi/skills`, `~/.pi/agent/skills`, `.agent

| `hooks`       | `https://github.com/earendil-works/pi/blob/main/packages/coding-agent/src/core/extensions/types.ts` (per-event contracts since v0.87.0; `docs/extensions.md` is now an overview) | Extension lifecycle events (`session_start`

| `permissions` | `https://pi.dev/docs/latest/settings`                                                                                                                                            | `defaultTools` in `.pi/settings.json` / `~/

Beyond `AGENTS.md`, Pi loads two system-prompt instruction files (docs: `https://pi.dev/docs/latest/usage`):

| Feature       | Official docs                                                                 | Upstream surface                                                                                                                              

| ------------- | ----------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------

| index         | `https://qwenlm.github.io/qwen-code-docs/en/`                                 | Qwen Code documentation index                                                                                                                 

| settings      | `https://qwenlm.github.io/qwen-code-docs/en/users/configuration/settings/`    | The exhaustive `settings.json` key table — the primary source for every `tools.*` / `security.*` / `permissions.*` key, and the first page to 

| `rules`       | `https://qwenlm.github.io/qwen-code-docs/en/users/features/memory/`           | Context files such as `QWEN.md`, plus the personal `QWEN.local.md` overlay (v0.16.2), hierarchical instructional context                      

| `ignore`      | `https://qwenlm.github.io/qwen-code-docs/en/users/configuration/qwen-ignore/` | `.qwenignore`, `context.fileFiltering.respectQwenIgnore`                                                                                      

| `mcp`         | `https://qwenlm.github.io/qwen-code-docs/en/users/features/mcp/`              | `mcpServers` inside `settings.json` at either scope. There is **no documented project-root `.mcp.json`** — re-checked at `v0.23.0` and `main`,

| `commands`    | `https://qwenlm.github.io/qwen-code-docs/en/users/features/commands/`         | `<project>/.qwen/commands/*.md` (higher precedence) and `~/.qwen/commands/*.md`; a nested directory becomes a `:`-namespaced command (`.qwen/c

| `subagents`   | `https://qwenlm.github.io/qwen-code-docs/en/users/features/sub-agents/`       | `<project>/.qwen/agents/*.md` (highest precedence) and `~/.qwen/agents/*.md`; Claude Code agent files are accepted in the same directory, incl

| `skills`      | `https://qwenlm.github.io/qwen-code-docs/en/users/features/skills/`           | `<project>/.qwen/skills/<name>/SKILL.md` and `~/.qwen/skills/<name>/SKILL.md`. Generated skills are namespaced (`auto-skill-*`, `learned-skill

| `hooks`       | `https://qwenlm.github.io/qwen-code-docs/en/users/features/hooks/`            | A `hooks` block in the layered `settings.json` at either scope; PascalCase event names, matcher-aware on the tool events                      

| `permissions` | `https://qwenlm.github.io/qwen-code-docs/en/users/features/approval-mode/`    | `permissions.allow` / `ask` / `deny` plus the `tools` and `security` groups of `settings.json`; approval mode and tool approval controls      

| `checks`      | `https://qwenlm.github.io/qwen-code-docs/en/users/features/code-review/`      | `<project>/.qwen/review-rules.md` — the native review-guidance file `/review` reads first. See below                                          

| Feature       | Official docs                                    | Upstream surface                                                               | | ------------- | ------------------------------------------------ | ---------------------

| ------------- | ------------------------------------------------ | ------------------------------------------------------------------------------ | | index         | `https://docs.replit.com/features/agent`         | Replit Agent document

| index         | `https://docs.replit.com/features/agent`         | Replit Agent documentation                                                     |

| `rules`       | `https://docs.replit.com/features/agent`         | Replit Agent project context                                                   |

| `commands`    | No dedicated upstream commands surface in map    | No Rulesync-supported Replit commands target in map                            | | `subagents`   | No dedicated upstream subagents surface in map   | No Rulesync-supported

| `subagents`   | No dedicated upstream subagents surface in map   | No Rulesync-supported Replit subagents target in map                           | | `skills`      | `https://docs.replit.com/features/agent/skills`  | Project `/.agents/ski

| `skills`      | `https://docs.replit.com/features/agent/skills`  | Project `/.agents/skills`, Agent Skills standard, Skills pane and `npx skills` |

| Feature       | Official docs                                            | Upstream surface                                                        | | ------------- | -------------------------------------------------------- | ------------

| ------------- | -------------------------------------------------------- | ----------------------------------------------------------------------- | | index         | `https://docs.roocode.com/`                              | Roo Code doc

| index         | `https://docs.roocode.com/`                              | Roo Code documentation index and shutdown notice                        |

| `rules`       | `https://docs.roocode.com/features/custom-instructions`  | `.roo/rules`, `.roorules`, mode-specific rules, AGENTS.md compatibility |

| `ignore`      | `https://docs.roocode.com/features/rooignore`            | `.rooignore` file surface                                               |

| `mcp`         | `https://docs.roocode.com/features/mcp/using-mcp-in-roo` | MCP server configuration                                                |

| `commands`    | `https://docs.roocode.com/features/slash-commands`       | `.roo/commands` reusable command files                                  |

| `subagents`   | `https://docs.roocode.com/features/custom-modes`         | Custom modes and orchestrator-style delegation                          |

| `skills`      | `https://docs.roocode.com/features/skills`               | Roo skills surface                                                      |

| Feature       | Official docs                                                                       | Upstream surface                                                                             | | ------------- | -----------------------

| ------------- | ----------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------- | | index         | `https://support.atlass

| index         | `https://support.atlassian.com/rovo/docs/use-rovo-dev-cli/`                         | Rovo Dev CLI documentation index                                                             |

| `rules`       | `https://support.atlassian.com/rovo/docs/use-memory-in-rovo-dev-cli/`               | User memory `~/.rovodev/AGENTS.md`, project `AGENTS.md`, `AGENTS.local.md`, legacy migration |

| `ignore`      | No dedicated upstream ignore surface in map                                         | No Rulesync-supported Rovo Dev ignore target in map                                          | | `mcp`         | `https://support.atlass

| `mcp`         | `https://support.atlassian.com/rovo/docs/connect-to-an-mcp-server-in-rovo-dev-cli/` | MCP server configuration in Rovo Dev CLI                                                     |

| `commands`    | `https://support.atlassian.com/rovo/docs/save-and-reuse-a-prompt-in-rovo-dev-cli/`  | Saved prompts: `.rovodev/prompts.yml` (+ `content_file` bodies), project/user/built-in tiers |

| `subagents`   | `https://support.atlassian.com/rovo/docs/use-subagents-in-rovo-dev-cli/`            | `.rovodev/subagents`, `~/.rovodev/subagents`, Markdown files with YAML frontmatter           |

| `skills`      | `https://support.atlassian.com/rovo/docs/extend-rovo-dev-cli-with-agent-skills/`    | `.rovodev/skills`, Agent Skills directories                                                  |

| `hooks`       | `https://support.atlassian.com/rovo/docs/rovo-dev-cli-commands/`                    | `/hooks` manages event hooks upstream; no page documents the config schema (blocked, #1986)  |

| `permissions` | `https://support.atlassian.com/rovo/docs/use-tools-in-rovo-dev-cli/`                | Tool controls exist upstream                                                                 |

| Feature       | Official docs                                                    | Upstream surface                                                                                       | | ------------- | --------------------------------

| ------------- | ---------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------ | | index         | `https://github.com/nrslib/takt`

| index         | `https://github.com/nrslib/takt`                                 | TAKT repository                                                                                        |

| `rules`       | `https://nrslib.com/faceted-prompting/`                          | Faceted prompting policies                                                                             |

| `ignore`      | No dedicated upstream ignore surface in map                      | No Rulesync-supported TAKT ignore target in map                                                        | | `mcp`         | `https://github.com/nrslib/takt/

| `mcp`         | `https://github.com/nrslib/takt/blob/main/docs/configuration.md` | `workflow_mcp_servers` transport allowlist in `config.yaml` (per-step `mcp_servers` not representable) |

| `commands`    | `https://nrslib.com/faceted-prompting/`                          | Faceted prompting instructions                                                                         |

| `subagents`   | `https://nrslib.com/faceted-prompting/`                          | Faceted prompting personas                                                                             |

| `skills`      | `https://nrslib.com/faceted-prompting/`                          | Faceted prompting knowledge                                                                            |

| Feature       | Official docs                                                 | Upstream surface                                                                                                                                              

| ------------- | ------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------

| index         | `https://docs.warp.dev/`                                      | Warp documentation index                                                                                                                                      

| `rules`       | `https://docs.warp.dev/agents/capabilities/rules/`            | Global Rules, Project Rules, `AGENTS.md`, `WARP.md`, global `~/.agents/AGENTS.md`, imported legacy rules                                                      

| `ignore`      | `https://docs.warp.dev/agents/capabilities/codebase-context/` | `.warpindexingignore` (project root, gitignore syntax)                                                                                                        

| `mcp`         | `https://docs.warp.dev/agents/capabilities/mcp/`              | `.warp/.mcp.json` (project) and `~/.warp/.mcp.json` (global)                                                                                                  

| `commands`    | `https://docs.warp.dev/agents/capabilities/skills/`           | Emitted onto the native skills surface (`/{skill-name}` invocation)                                                                                           

| `subagents`   | No dedicated upstream subagents surface in map                | No Rulesync-supported Warp subagents target in map (child agents are runtime constructs, no file format)                                                      

| `skills`      | `https://docs.warp.dev/agents/capabilities/skills/`           | `.warp/skills/` and `.agents/skills/`, ahead of the `.claude/` … `.opencode/` compatibility roots; treat the ordering as low-confidence (the capabilities page

| `permissions` | `https://docs.warp.dev/terminal/settings/all-settings/`       | `settings.toml` `[agents.execution_profiles.<id>]` (current) and legacy `[agents.profiles]` keys                                                              

| Feature       | Official docs                                          | Upstream surface                                                                  | | ------------- | ------------------------------------------------------ | ------

| ------------- | ------------------------------------------------------ | --------------------------------------------------------------------------------- | | index         | `https://docs.windsurf.com/`                           | Windsu

| index         | `https://docs.windsurf.com/`                           | Windsurf documentation index                                                      |

| `rules`       | `https://docs.windsurf.com/windsurf/cascade/memories`  | `.windsurf/rules/*.md`, global rules, AGENTS.md, activation modes                 |

| `ignore`      | No dedicated upstream ignore surface in map            | Rulesync maps a Windsurf ignore target; verify upstream before expanding behavior | | `mcp`         | `https://docs.windsurf.com/windsurf/cascade/mcp`       | MCP se

| `mcp`         | `https://docs.windsurf.com/windsurf/cascade/mcp`       | MCP server configuration with stdio, HTTP, and SSE transports                     |

| `commands`    | `https://docs.windsurf.com/windsurf/cascade/workflows` | Cascade workflows as Markdown files invoked via slash commands                    |

| `subagents`   | No dedicated upstream subagents surface in map         | No Rulesync-supported Windsurf subagents target in map                            | | `skills`      | `https://docs.windsurf.com/windsurf/cascade/skills`    | Skills

| `skills`      | `https://docs.windsurf.com/windsurf/cascade/skills`    | Skills as bundled procedures with supporting files                                |

| `hooks`       | `https://docs.windsurf.com/windsurf/cascade/hooks`     | Cascade pre/post hooks for shell commands at workflow events                      |

| Feature       | Official docs                                                                                                              | Upstream surface                                                                                 

| ------------- | -------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------

| index         | `https://zed.dev/docs/ai/overview`                                                                                         | Zed AI documentation index                                                                       

| `rules`       | `https://zed.dev/docs/ai/instructions`                                                                                     | `.rules`, AGENTS.md-compatible files, global instructions, Rules Library                         

| `ignore`      | `https://zed.dev/docs/reference/all-settings#private-files`                                                                | `.zed/settings.json`, `private_files` glob list (`ExtendingVec`, accumulates across scopes)      

| `mcp`         | `https://zed.dev/docs/ai/mcp`                                                                                              | `context_servers` in `.zed/settings.json` / global `settings.json`                               

| `commands`    | No dedicated upstream commands surface in map                                                                              | Skills double as `/name` slash commands; no native command files (discussion zed-industries/zed#5

| `subagents`   | No dedicated upstream subagents surface in map                                                                             | Agent profiles and `spawn_agent` are runtime settings, not per-agent definition files            

| `skills`      | `https://zed.dev/docs/ai/skills`                                                                                           | Agent Skills (`SKILL.md`); `disable-model-invocation`; description limit counted in characters si

| `permissions` | `https://zed.dev/docs/ai/tool-permissions`, `https://zed.dev/docs/ai/sandboxing`, `https://zed.dev/docs/ai/agent-profiles` | `agent.tool_permissions`, `sandbox_permissions`, `agent.profiles`, `agent.default_profile`       

- Suspicious external URLs/API connections      - Privilege escalation or token misuse      - Malicious command execution (`curl | bash`, `eval`, base64 decode execution)

- Privilege escalation or token misuse      - Malicious command execution (`curl | bash`, `eval`, base64 decode execution)      - Supply chain attack patterns (suspicious npm packages, unsigned action references)

- Malicious command execution (`curl | bash`, `eval`, base64 decode execution)

- Malicious command execution (`curl | bash`, `eval`, base64 decode execution)

Apache License                            Version 2.0, January 2004                         http://www.apache.org/licenses/

http://www.apache.org/licenses/

http://www.apache.org/licenses/LICENSE-2.0

Executable file

Executable file

Executable file

*/ function downloadUrl(asset: string): string {   return `https://github.com/dyoshikawa/rulesync/releases/download/v#{version}/${asset}`;

*/ function downloadUrl(asset: string): string {   return `https://github.com/dyoshikawa/rulesync/releases/download/v#{version}/${asset}`;

function downloadUrl(asset: string): string {   return `https://github.com/dyoshikawa/rulesync/releases/download/v#{version}/${asset}`; }

function downloadUrl(asset: string): string {   return `https://github.com/dyoshikawa/rulesync/releases/download/v#{version}/${asset}`; }

return `https://github.com/dyoshikawa/rulesync/releases/download/v#{version}/${asset}`;

return `https://github.com/dyoshikawa/rulesync/releases/download/v#{version}/${asset}`;

class Rulesync < Formula   desc "Unified AI rules management CLI that generates config files for AI dev tools"   homepage "https://github.com/dyoshikawa/rulesync"

class Rulesync < Formula   desc "Unified AI rules management CLI that generates config files for AI dev tools"   homepage "https://github.com/dyoshikawa/rulesync"

desc "Unified AI rules management CLI that generates config files for AI dev tools"   homepage "https://github.com/dyoshikawa/rulesync"   version "${version}"

desc "Unified AI rules management CLI that generates config files for AI dev tools"   homepage "https://github.com/dyoshikawa/rulesync"   version "${version}"

homepage "https://github.com/dyoshikawa/rulesync"

homepage "https://github.com/dyoshikawa/rulesync"