Not in the top 1,000 by GitHub stars
disler/learning-cmux-with-agents
31 natural-language prompts that prove one primary agent can stand up, drive, and tear down a whole fleet of AI coding agents and terminals inside cmux.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
ai_docs/cmux-skills/cmux/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6eaacabbee4c → 6eaacabbee4c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6eaacabbee4c
No earlier version was observed for comparison.
ai_docs/cmux-skills/cmux-architecture/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6eaacabbee4c → 6eaacabbee4c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6eaacabbee4c
No earlier version was observed for comparison.
ai_docs/cmux-skills/cmux-backend/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6eaacabbee4c → 6eaacabbee4c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6eaacabbee4c
No earlier version was observed for comparison.
ai_docs/cmux-skills/cmux-browser/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
6eaacabbee4c → 6eaacabbee4c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 6eaacabbee4c
No earlier version was observed for comparison.
ai_docs/cmux-skills/cmux-custom-sidebar/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6eaacabbee4c → 6eaacabbee4c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6eaacabbee4c
No earlier version was observed for comparison.
ai_docs/cmux-skills/cmux-customization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6eaacabbee4c → 6eaacabbee4c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6eaacabbee4c
No earlier version was observed for comparison.
ai_docs/cmux-skills/cmux-debugging/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6eaacabbee4c → 6eaacabbee4c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6eaacabbee4c
No earlier version was observed for comparison.
ai_docs/cmux-skills/cmux-dev-workflow/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6eaacabbee4c → 6eaacabbee4c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6eaacabbee4c
No earlier version was observed for comparison.
ai_docs/cmux-skills/cmux-diagnostics/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
6eaacabbee4c → 6eaacabbee4c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 6eaacabbee4c
No earlier version was observed for comparison.
ai_docs/cmux-skills/cmux-ghostty/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6eaacabbee4c → 6eaacabbee4c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6eaacabbee4c
No earlier version was observed for comparison.
ai_docs/cmux-skills/cmux-keyboard-shortcuts/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6eaacabbee4c → 6eaacabbee4c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6eaacabbee4c
No earlier version was observed for comparison.
ai_docs/cmux-skills/cmux-localization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6eaacabbee4c → 6eaacabbee4c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6eaacabbee4c
No earlier version was observed for comparison.
ai_docs/cmux-skills/cmux-markdown/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6eaacabbee4c → 6eaacabbee4c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6eaacabbee4c
No earlier version was observed for comparison.
ai_docs/cmux-skills/cmux-release/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6eaacabbee4c → 6eaacabbee4c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6eaacabbee4c
No earlier version was observed for comparison.
ai_docs/cmux-skills/cmux-settings/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
6eaacabbee4c → 6eaacabbee4c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 6eaacabbee4c
No earlier version was observed for comparison.
ai_docs/cmux-skills/cmux-shared-behavior/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6eaacabbee4c → 6eaacabbee4c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6eaacabbee4c
No earlier version was observed for comparison.
ai_docs/cmux-skills/cmux-socket-policy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6eaacabbee4c → 6eaacabbee4c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6eaacabbee4c
No earlier version was observed for comparison.
ai_docs/cmux-skills/cmux-testing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6eaacabbee4c → 6eaacabbee4c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6eaacabbee4c
No earlier version was observed for comparison.
ai_docs/cmux-skills/cmux-workspace/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6eaacabbee4c → 6eaacabbee4c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6eaacabbee4c
No earlier version was observed for comparison.
Verified commit 6eaacabbee4c71120f7cd161c9539530f84068a8
git clone --filter=blob:none --no-checkout https://github.com/disler/learning-cmux-with-agents.git .hotskills/disler-learning-cmux-with-agents && git -C .hotskills/disler-learning-cmux-with-agents checkout --detach 6eaacabbee4c71120f7cd161c9539530f84068a8
# Copy each selected skill directory from .hotskills/disler-learning-cmux-with-agents into .claude/skills/<skill-name>/Heat
0.2- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- cmux
ai_docs/cmux-skills/cmux - cmux-architecture
ai_docs/cmux-skills/cmux-architecture - cmux-backend
ai_docs/cmux-skills/cmux-backend - cmux-browser
ai_docs/cmux-skills/cmux-browser - cmux-custom-sidebar
ai_docs/cmux-skills/cmux-custom-sidebar - cmux-customization
ai_docs/cmux-skills/cmux-customization - cmux-debugging
ai_docs/cmux-skills/cmux-debugging - cmux-dev-workflow
ai_docs/cmux-skills/cmux-dev-workflow - cmux-diagnostics
ai_docs/cmux-skills/cmux-diagnostics - cmux-ghostty
ai_docs/cmux-skills/cmux-ghostty - cmux-keyboard-shortcuts
ai_docs/cmux-skills/cmux-keyboard-shortcuts - cmux-localization
ai_docs/cmux-skills/cmux-localization - cmux-markdown
ai_docs/cmux-skills/cmux-markdown - cmux-release
ai_docs/cmux-skills/cmux-release - cmux-settings
ai_docs/cmux-skills/cmux-settings - cmux-shared-behavior
ai_docs/cmux-skills/cmux-shared-behavior - cmux-socket-policy
ai_docs/cmux-skills/cmux-socket-policy - cmux-testing
ai_docs/cmux-skills/cmux-testing - cmux-workspace
ai_docs/cmux-skills/cmux-workspace
How it works
cmux
When your agent uses it
End-user control of cmux topology and routing (windows, workspaces, panes/surfaces, focus, moves, reorder, identify, trigger flash). Use when automation needs deterministic placement and navigation in a multi-pane cmux layout.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
858 tokensWhen the skill is activated
Reference documents
6,738 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Concepts
- Fast Start
- Settings and Docs
- Handle Model
- Deep-Dive References
Files
../cmux-browser/SKILL.mddoc5,343 bytes../cmux-markdown/SKILL.mddoc3,465 bytes../cmux-settings/SKILL.mddoc5,935 bytes../cmux-workspace/SKILL.mddoc10,397 bytesSKILL.mdcore3,465 bytesSKILL.mdcore3,465 bytesSKILL.mdcore3,465 bytesSKILL.mdcore3,465 bytesSKILL.mdcore3,465 bytesagents/openai.yamlasset349 bytesreferences/handles-and-identify.mddoc774 bytesreferences/panes-surfaces.mddoc988 bytesreferences/trigger-flash-and-health.mddoc493 bytesreferences/windows-workspaces.mddoc594 bytes
Read SKILL.md
# cmux Core Control
Use this skill to control non-browser cmux topology and routing.
## Core Concepts
- Window: top-level macOS cmux window.
- Workspace: tab-like group within a window.
- Pane: split container in a workspace.
- Surface: a tab within a pane (terminal or browser panel).
## Fast Start
```bashView the complete source on GitHubcmux-architecture
When your agent uses it
cmux package architecture, refactor layering, dependency inversion, file organization, DocC documentation, package design discipline, testability, and Swift 6 concurrency rules. Use before adding or meaningfully rewriting Swift files, Swift packages, coordinators, services, repositories, or public package APIs.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
5,438 tokensWhen the skill is activated
Reference documents
2,080 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Package architecture
- Refactor architecture: layers, Coordinator/Service/Repository, dependency inversion
- File organization
- Documentation
- Package design discipline
- Testability
- Modern Swift concurrency
- Detailed references
Files
SKILL.mdcore24,171 bytesSKILL.mdcore24,171 bytesSKILL.mdcore24,171 bytesagents/openai.yamlasset352 bytesreferences/concurrency-carveouts.mddoc3,856 bytesreferences/file-api-discipline.mddoc2,472 bytesreferences/package-boundaries.mddoc3,328 bytes
Read SKILL.md
# cmux Architecture
## Package architecture
We are migrating cmux from a single app target into Swift Packages under `Packages/`. Every new package must satisfy three rules:
- **Ergonomic.** Public API surface matches what callers naturally want to write. Default to internal access; expose `public` only for types and functions that downstream consumers actually use. Avoid friction such as forcing every call site through a builder or wrapper when a direct API is fine.
- **No dependency cycles.** Packages form a strict DAG. A package may only depend on packages strictly lower in the graph. When two packages need to share a type, lift it to a common lower-level package or define a protocol seam in the consumer. Every new dependency edge requires re-checking that the graph stays acyclic.
- **Clear but not overly narrow responsibilities.** A package owns one full domain (e.g. _settings_, _appearance_, _workspace_, _terminal_, _browser_, _command palette_), not a slice of one. A package called "appearance math" or "workspace model" is too narrow — it forces every consumer that touches the surrounding domain to also depend on the sibling slices. Prefer a single `CmuxAppearance` that owns settings, theming, colors, glass, and snapshots together, over `CmuxAppearanceMath` + `CmuxAppearanceTheme` + `CmuxAppearanceSettings`. Don't fragment a domain into `CmuxFooFormatting` + `CmuxFooLogic` + `CmuxFooState` — that's folder structure inside a single package, not module structure. A package boundary exists because more than one consumer needs the contents, or a build/test seam needs to exist.
When in doubt, **extract leaf-first**: pull out the package that has no internal dependencies. Consumers in the app target stay put and only update imports. Each leaf shrinks the app target without requiring downstream packages to exist yet.
The existing packages under `Packages/` predate this policy and should not be used as design references.
View the complete source on GitHubcmux-backend
When your agent uses it
Backend TypeScript and Cloud VM development rules for cmux. Use when editing web/app/api, web/services, backend scripts, Cloud VM lifecycle, provider integrations, Postgres, Stack Auth pricing gates, migrations, or provider image build scripts.
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
683 tokensWhen the skill is activated
Reference documents
991 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core rules
- Secrets
- Detailed references
Files
SKILL.mdcore2,947 bytesSKILL.mdcore2,947 bytesSKILL.mdcore2,947 bytesSKILL.mdcore2,947 bytesagents/openai.yamlasset329 bytesreferences/cloud-vm-control-plane.mddoc2,255 bytesreferences/effect-boundaries.mddoc2,802 bytes
Read SKILL.md
# cmux Backend
Use this skill for backend TypeScript, Cloud VM, provider, database, auth, rate-limit, retry, timeout, or telemetry work.
## Core rules
- Default backend TypeScript to Effect under `web/app/api/**`, `web/services/**`, and backend scripts that touch providers, databases, auth, rate limits, retries, timeouts, or telemetry.
- Keep Next route handlers thin: parse the request, run one Effect program at the boundary, map typed errors to HTTP responses, and treat unexpected defects separately.
- Use plain TypeScript only for trivial data shapes, constants, config files, frontend React code, or small glue where Effect would add ceremony without improving failure handling.
- Cloud VM backend logic must stay in Vercel route handlers and Effect services backed by Postgres.
- Do not reintroduce Rivet or a raw actor protocol for Cloud VM unless a later architecture doc explicitly changes the control plane.
- Production and staging Cloud VM Postgres use the Vercel Marketplace AWS Aurora PostgreSQL OIDC/RDS IAM path.
- Runtime env names are `CMUX_DB_DRIVER=aws-rds-iam`, `AWS_ROLE_ARN`, `AWS_REGION`, `PGHOST`, `PGPORT`, `PGUSER`, and `PGDATABASE`.
- Run production/staging migrations with `bun db:migrate:aws-rds-iam`; never run Drizzle migrations from Vercel build or route startup.View the complete source on GitHubcmux-browser
When your agent uses it
End-user browser automation with cmux. Use when you need to open sites, interact with pages, wait for state changes, and extract data from cmux browser surfaces.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
1,272 tokensWhen the skill is activated
Reference documents
3,636 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Workflow
- Surface Targeting
- Wait Support
- Common Flows
- Deep-Dive References
- Ready-to-Use Templates
- Limits (WKWebView)
- Troubleshooting
Scripts executed separately
templates/authenticated-session.shtemplates/capture-workflow.shtemplates/form-automation.sh
Files
SKILL.mdcore5,343 bytesSKILL.mdcore5,343 bytesSKILL.mdcore5,343 bytesSKILL.mdcore5,343 bytesSKILL.mdcore5,343 bytesSKILL.mdcore5,343 bytesSKILL.mdcore5,343 bytesSKILL.mdcore5,343 bytesagents/openai.yamlasset327 bytesreferences/authentication.mddoc3,591 bytesreferences/commands.mddoc4,064 bytesreferences/proxy-support.mddoc1,059 bytesreferences/session-management.mddoc2,200 bytesreferences/snapshot-refs.mddoc1,830 bytesreferences/video-recording.mddoc1,440 bytestemplates/authenticated-session.shruns555 bytestemplates/capture-workflow.shruns377 bytestemplates/form-automation.shruns360 bytes
Read SKILL.md
# Browser Automation with cmux
Use this skill for browser tasks inside cmux webviews.
## Core Workflow
1. Open or target a browser surface.
2. Verify navigation with `get url` before waiting or snapshotting.
3. Snapshot (`--interactive`) to get fresh element refs.
4. Act with refs (`click`, `fill`, `type`, `select`, `press`).
5. Wait for state changes.
6. Re-snapshot after DOM/navigation changes.
```bashView the complete source on GitHubcmux-custom-sidebar
When your agent uses it
Build a custom cmux sidebar from a plain-language request. Use when the user asks for a custom sidebar, a sidebar that shows their workspaces/tabs/PRs/clock, a vibe-coded sidebar, or anything involving files in ~/.config/cmux/sidebars/. Covers authoring the interpreted SwiftUI-style file, enabling the beta flag, selecting it, and iterating with hot reload.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
1,689 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Full reference
- Workflow
- Authoring rules
- Quick start
- Live data context (read-only, refreshes ~1s)
- Actions
- Supported subset at a glance
- Troubleshooting
Files
SKILL.mdcore6,694 bytesSKILL.mdcore6,694 bytesSKILL.mdcore6,694 bytesSKILL.mdcore6,694 bytes
Read SKILL.md
# cmux Custom Sidebar
cmux renders custom sidebars from a small SwiftUI-style file at runtime: no Xcode, no build step, no signing. The file hot-reloads on save, binds to live cmux state (workspaces, tabs, git, PRs, clock), and can run real cmux commands on tap.
The person asking is usually describing a result ("a sidebar that shows my workspaces and lets me jump between them"), not an implementation. Turn that into a clean, native-looking sidebar and make the engineering decisions for them. Do not ask them about SwiftUI, files, or syntax.
## Full reference
This skill is the workflow summary. The complete authoring contract (every supported view, modifier, language feature, and data field) is one command away; read it before writing a non-trivial sidebar:
```bash
cmux docs sidebars
curl -fsSL https://raw.githubusercontent.com/manaflow-ai/cmux/main/docs/custom-sidebars.md
```View the complete source on GitHubcmux-customization
When your agent uses it
Customize cmux for an end user. Use when changing cmux.json actions, custom commands, workspace layouts, plus-button behavior, surface tab bar buttons, Command Palette entries, Dock controls, sidebar and app settings, shortcuts, notifications, browser routing, examples-library presets, or Ghostty-backed terminal preferences.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
2,375 tokensWhen the skill is activated
Reference documents
1,996 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What Can Be Customized
- Choose the Right Surface
- Examples Library
- Workflow
- Common Patterns
- Validation
- Rules
Files
SKILL.mdcore9,783 bytesSKILL.mdcore9,783 bytesSKILL.mdcore9,783 bytesSKILL.mdcore9,783 bytesSKILL.mdcore9,783 bytesagents/openai.yamlasset255 bytesreferences/examples.mddoc8,278 bytes
Read SKILL.md
# cmux Customization
Use this skill for user-facing cmux customization. Keep the user's config intact, prefer schema-backed edits, and validate before reporting completion.
## What Can Be Customized
- Custom actions: define reusable `actions` in `cmux.json`. Actions can appear in Cmd+Shift+P, surface tab bars, shortcuts, and the plus-button right-click menu.
- New workspace button: set `ui.newWorkspace.action` to replace the normal plus-button click, and `ui.newWorkspace.contextMenu` to control right-click actions. `ui.newWorkspace.rightClick` is accepted as an alias, but new examples should use `contextMenu`.
- Surface tab bar buttons: set `ui.surfaceTabBar.buttons` to replace the default tab bar buttons. Include built-in IDs such as `cmux.newTerminal`, `cmux.newBrowser`, `cmux.splitRight`, and `cmux.splitDown` only when they should stay visible.
- Workflows and layouts: use `commands` with workspace definitions to open a worktree, multiple checkouts, local services, browser previews, or SSH sessions in a deliberate split layout.
- Dock controls: create `.cmux/dock.json` or `~/.config/cmux/dock.json` for right-sidebar terminal controls such as logs, test watchers, git TUIs, dev servers, queues, or `cmux feed tui --opentui`.
- Sidebar and app behavior: use `cmux-settings` for supported settings such as appearance, sidebar display, notification behavior, browser routing, automation, shortcuts, and new-workspace placement.
- Workspace metadata: use the cmux CLI or `cmux-workspace` for workspace names, descriptions, colors, read state, and sidebar metadata updates.
- Feed and notifications: use `cmux hooks setup` for Feed event sources, notification settings for delivery behavior, and notification hooks in `cmux.json` for filtering or post-processing banners.View the complete source on GitHubcmux-debugging
When your agent uses it
Debug logging, Debug menu, runtime pitfalls, typing-latency-sensitive paths, SwiftUI list snapshot boundaries, OS-version repros, and local visual iteration for cmux. Use when adding debug probes, diagnosing UI/runtime issues, touching terminal rendering, tab/sidebar list views, drag/drop UTTypes, or using the Debug menu.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
1,012 tokensWhen the skill is activated
Reference documents
1,403 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Debug event log
- Debug menu
- Runtime pitfalls
- Detailed references
Files
SKILL.mdcore4,266 bytesSKILL.mdcore4,266 bytesagents/openai.yamlasset358 bytesreferences/debug-event-log.mddoc1,959 bytesreferences/runtime-pitfalls.mddoc4,046 bytes
Read SKILL.md
# cmux Debugging
## Debug event log
When adding debug event instrumentation, put events (keys, mouse, focus, splits, tabs) in the unified DEBUG build log. This is not a blanket requirement to add logs to every new code path. Most temporary probes should be added only during the dogfood debug loop and removed before merge.
```bash
tail -f "$(cat /tmp/cmux-last-debug-log-path 2>/dev/null || echo /tmp/cmux-debug.log)"
```
- Untagged Debug app: `/tmp/cmux-debug.log`
- Tagged Debug app (`./scripts/reload.sh --tag <tag>`): `/tmp/cmux-debug-<tag>.log`
- `reload.sh` writes the current path to `/tmp/cmux-last-debug-log-path`
- `reload.sh` writes the selected dev CLI path to `/tmp/cmux-last-cli-path`View the complete source on GitHubcmux-dev-workflow
When your agent uses it
Contributor workflow rules for cmux setup, Xcode project normalization, tagged sidebar ExtensionKit development, and dev builds. Use when setting up the cmux repo, changing Xcode project files, adding sidebar extensions, or working with tagged debug builds.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
1,449 tokensWhen the skill is activated
Reference documents
1,279 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Tagged local dev
- Initial setup
- Xcode toolchain
- Sidebar extension point (dev tagging)
- Detailed references
Files
SKILL.mdcore6,003 bytesSKILL.mdcore6,003 bytesSKILL.mdcore6,003 bytesSKILL.mdcore6,003 bytesSKILL.mdcore6,003 bytesSKILL.mdcore6,003 bytesSKILL.mdcore6,003 bytesagents/openai.yamlasset330 bytesreferences/sidebar-extension-tagging.mddoc2,117 bytesreferences/tagged-builds.mddoc1,788 bytesreferences/xcode-project-normalization.mddoc1,207 bytes
Read SKILL.md
# cmux Dev Workflow
## Tagged local dev
After making code changes, always run the reload script with a tag to build the Debug app:
```bash
./scripts/reload.sh --tag <short-tag>
```
By default, `reload.sh` builds but does not launch the app. Pass `--launch` only when you need to open it automatically.
Never run bare `xcodebuild` or open an untagged `cmux DEV.app`. Untagged builds share the default debug socket and bundle ID with other agents, causing conflicts and stealing focus.
View the complete source on GitHubcmux-diagnostics
When your agent uses it
Run end-user cmux diagnostics. Use when cmux hooks, notifications, session restore, settings, browser automation, socket access, CLI control, or agent resume behavior is not working, or when the user asks for a cmux health check, doctor report, or support-safe debug summary.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
831 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Report
- What to Check
- Interpretation
- Rules
Scripts executed separately
scripts/cmux-diagnostics
Files
SKILL.mdcore3,680 bytesSKILL.mdcore3,680 bytesSKILL.mdcore3,680 bytesSKILL.mdcore3,680 bytesSKILL.mdcore3,680 bytesSKILL.mdcore3,680 bytesSKILL.mdcore3,680 bytesSKILL.mdcore3,680 bytesSKILL.mdcore3,680 bytesagents/openai.yamlasset249 bytesscripts/cmux-diagnosticsruns6,045 bytes
Read SKILL.md
# cmux Diagnostics
Use this skill to collect and interpret support-safe cmux diagnostics for end users. Default to read-only checks. Do not dump hook config files, session stores, prompt logs, tokens, or environment secrets.
## Quick Report
Run the bundled read-only diagnostic script first:
```bash
# From a cmux checkout
skills/cmux-diagnostics/scripts/cmux-diagnostics
# From an installed skill
~/.agents/skills/cmux-diagnostics/scripts/cmux-diagnosticsView the complete source on GitHubcmux-ghostty
When your agent uses it
Ghostty submodule and GhosttyKit workflow rules for cmux. Use when modifying the ghostty submodule, rebuilding GhosttyKit.xcframework, updating the parent submodule pointer, or documenting fork conflict notes.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
409 tokensWhen the skill is activated
Reference documents
415 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- GhosttyKit builds
- Submodule workflow
- Submodule safety
- Detailed reference
Files
SKILL.mdcore1,664 bytesSKILL.mdcore1,664 bytesSKILL.mdcore1,664 bytesSKILL.mdcore1,664 bytesSKILL.mdcore1,664 bytesSKILL.mdcore1,664 bytesagents/openai.yamlasset345 bytesreferences/submodule-safety.mddoc1,810 bytes
Read SKILL.md
# cmux Ghostty
## GhosttyKit builds
When rebuilding GhosttyKit.xcframework, always use Release optimizations:
```bash
cd ghostty && zig build -Demit-xcframework=true -Dxcframework-target=universal -Doptimize=ReleaseFast
```
## Submodule workflow
Ghostty changes must be committed in the `ghostty` submodule and pushed to the `manaflow-ai/ghostty` fork. Keep `docs/ghostty-fork.md` up to date with any fork changes and conflict notes.
View the complete source on GitHubcmux-keyboard-shortcuts
When your agent uses it
Guide and apply cmux keyboard shortcut customization. Use when the user asks to customize, rebind, unbind, reset, audit, or create shortcut templates for cmux, including tmux-style, Vim-style, terminal-first, browser-heavy, iTerm/Terminal-like, or agent-triage layouts.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
2,835 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Shortcut Model
- Workflow
- Preset Templates
- Rules
Files
SKILL.mdcore11,898 bytesSKILL.mdcore11,898 bytesSKILL.mdcore11,898 bytesSKILL.mdcore11,898 bytesSKILL.mdcore11,898 bytesSKILL.mdcore11,898 bytesSKILL.mdcore11,898 bytesSKILL.mdcore11,898 bytesSKILL.mdcore11,898 bytesSKILL.mdcore11,898 bytesSKILL.mdcore11,898 bytesSKILL.mdcore11,898 bytesSKILL.mdcore11,898 bytesSKILL.mdcore11,898 bytesagents/openai.yamlasset341 bytes
Read SKILL.md
# cmux-keyboard-shortcuts
Use this skill to turn a user's workflow preferences into cmux shortcut bindings in `~/.config/cmux/cmux.json`. It should guide the user, propose compact templates, apply selected changes, and confirm the config parses with recognized keys.
## Prerequisites
- Work from a cmux checkout or worktree root when possible.
- Use `skills/cmux-settings/scripts/cmux-settings` for every read/write. It reads JSONC, writes atomically, and validates JSON plus recognized settings keys.
- For action IDs, read `skills/cmux-settings/references/shortcut-actions.md`.
- For current defaults, read `web/data/cmux-shortcuts.ts` or `Sources/KeyboardShortcutSettings.swift`.
```bash
find_cmux_settings() {
local rootView the complete source on GitHubcmux-localization
When your agent uses it
Localization rules and audit workflow for cmux UI strings, settings rows, menus, shortcuts, schema/config text, docs, command/help text, alerts, tooltips, and web messages. Use whenever changing user-facing text.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
442 tokensWhen the skill is activated
Reference documents
452 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Hard rules
- Audit checklist
- Related shortcut rule
- Detailed reference
Files
SKILL.mdcore2,102 bytesagents/openai.yamlasset324 bytesreferences/audit-workflow.mddoc2,055 bytes
Read SKILL.md
# cmux Localization
Use this skill for any user-facing string change.
## Hard rules
- All user-facing strings must be localized.
- Use `String(localized: "key.name", defaultValue: "English text")` for Swift/AppKit/SwiftUI strings.
- Keys go in `Resources/Localizable.xcstrings` with translations for all supported languages, currently English and Japanese.
- Never use bare string literals in SwiftUI `Text()`, `Button()`, alert titles, tooltips, menus, or dialogs.
- Localization audit is required for every user-facing change.
- `defaultValue`, English fallback text, schema descriptions, or copied English strings do not count as localization.
- For localized web/docs content, update every supported message catalog, currently `web/messages/en.json` and `web/messages/ja.json`, plus any localized data structures carrying inline translations.
View the complete source on GitHubcmux-markdown
When your agent uses it
Open markdown files in a formatted viewer panel with live reload. Use when you need to display plans, documentation, or notes alongside the terminal with rich rendering (headings, code blocks, tables, lists).
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
804 tokensWhen the skill is activated
Reference documents
1,042 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Workflow
- When to Use
- Live File Watching
- Agent Integration
- Routing
- Deep-Dive References
- Rendering Support
Files
SKILL.mdcore3,465 bytesSKILL.mdcore3,465 bytesSKILL.mdcore3,465 bytesSKILL.mdcore3,465 bytesSKILL.mdcore3,465 bytesagents/openai.yamlasset353 bytesreferences/commands.mddoc1,699 bytesreferences/live-reload.mddoc2,729 bytes
Read SKILL.md
# Markdown Viewer with cmux
Use this skill to display markdown files in a dedicated panel with rich formatting and live file watching.
## Core Workflow
1. Write your plan or notes to a `.md` file.
2. Open it in a markdown panel.
3. The panel auto-updates when the file changes on disk.
```bash
# Open a markdown file as a split panel next to the current terminal
cmux markdown open plan.md
View the complete source on GitHubcmux-release
When your agent uses it
cmux release workflow, version bumping, changelog updates, pretag guard, release tags, and release asset expectations. Use when preparing or troubleshooting a cmux release.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
476 tokensWhen the skill is activated
Reference documents
444 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Version bumping
- Notes
- Detailed reference
Files
SKILL.mdcore1,921 bytesSKILL.mdcore1,921 bytesSKILL.mdcore1,921 bytesSKILL.mdcore1,921 bytesSKILL.mdcore1,921 bytesSKILL.mdcore1,921 bytesSKILL.mdcore1,921 bytesagents/openai.yamlasset326 bytesreferences/release-checklist.mddoc1,960 bytes
Read SKILL.md
# cmux Release
Use the `/release` command to prepare a new release. This will:
1. Determine the new version (bumps minor by default)
2. Gather commits since the last tag and update the changelog
3. Update `CHANGELOG.md` (the docs changelog page at `web/app/docs/changelog/page.tsx` reads from it)
4. Run `./scripts/bump-version.sh` to update both versions
5. Commit, run `./scripts/release-pretag-guard.sh`, tag, and push
## Version bumping
```bash
./scripts/bump-version.shView the complete source on GitHubcmux-settings
When your agent uses it
View and edit cmux settings in ~/.config/cmux/cmux.json. Use when the user wants to change cmux preferences (appearance, sidebar, notifications, automation, browser, shortcuts), set a value by JSON path, validate the file, open it in an editor, or look up which keys cmux recognizes. Triggers on '/cmux-settings', 'change cmux setting', 'set <something> in cmux', 'cmux config', 'cmux.json', or 'rebind a cmux shortcut'.
What it loads into context
Frontmatter
116 tokensAlways available to the agent
SKILL.md
1,461 tokensWhen the skill is activated
Reference documents
4,013 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Helper script
- Workflow
- Quick reference
- Rules
Scripts executed separately
scripts/cmux-settings
Files
SKILL.mdcore5,935 bytesSKILL.mdcore5,935 bytesSKILL.mdcore5,935 bytesSKILL.mdcore5,935 bytesSKILL.mdcore5,935 bytesagents/openai.yamlasset332 bytesreferences/all-keys.mddoc11,921 bytesreferences/shortcut-actions.mddoc4,078 bytesscripts/cmux-settingsruns13,856 bytes
Read SKILL.md
# cmux-settings
cmux reads user settings from `~/.config/cmux/cmux.json` (JSONC). The app installs a file watcher; saving the file applies changes immediately, no restart needed. Legacy `~/.config/cmux/settings.json` is read only as a fallback for keys not present in `cmux.json`.
Schema: `https://raw.githubusercontent.com/manaflow-ai/cmux/main/web/data/cmux.schema.json`. The authoritative path list lives in `Sources/CmuxSettingsJSONPathSupport.swift` in the cmux checkout, and the installed skill includes a generated copy in `references/all-keys.md`. Top-level sections are `app`, `terminal`, `notifications`, `sidebar`, `sidebarAppearance`, `workspaceColors`, `automation`, `browser`, and `shortcuts`. Non-settings sections (`actions`, `ui`, `commands`, `vault`, `rightSidebar`) coexist in the same file.
## Helper script
Use the bundled helper for every read/write. It strips JSONC comments, writes atomically, and validates keys against the schema.
```bash
# From a cmux checkout
skills/cmux-settings/scripts/cmux-settings <subcommand>
View the complete source on GitHubcmux-shared-behavior
When your agent uses it
Shared behavior and mutation-path rules for cmux. Use when a behavior is exposed through multiple entrypoints such as keyboard shortcuts, command palette, context menu, CLI, settings, debug menu, optimistic UI, or tests that previously missed a bug.
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
252 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Shared entrypoints
- Optimistic updates
- Missed-bug coverage
Files
SKILL.mdcore1,259 bytesagents/openai.yamlasset337 bytes
Read SKILL.md
# cmux Shared Behavior
Use one shared action/model path when behavior is exposed through multiple entrypoints.
## Shared entrypoints
When a behavior is exposed through multiple surfaces, implement one shared action/model path and verify every entrypoint that should invoke it.
Common entrypoints include:
- keyboard shortcut
- command palette
- context menu
- CLI/socket commandView the complete source on GitHubcmux-socket-policy
When your agent uses it
Socket command threading and focus policy for cmux CLI/socket work. Use when adding or changing socket commands, CLI commands, telemetry commands, focus/select/open/close/send-key behavior, or automation that could steal app focus.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
343 tokensWhen the skill is activated
Reference documents
410 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Threading policy
- Focus policy
- Detailed reference
Files
SKILL.mdcore1,670 bytesagents/openai.yamlasset348 bytesreferences/threading-and-focus.mddoc1,981 bytes
Read SKILL.md
# cmux Socket Policy
## Threading policy
- Do not use `DispatchQueue.main.sync` for high-frequency socket telemetry commands such as `report_*`, `ports_kick`, status/progress updates, or log metadata updates.
- For telemetry hot paths, parse and validate arguments off-main.
- Dedupe and coalesce off-main first.
- Schedule minimal UI/model mutation with `DispatchQueue.main.async` only when needed.
- Commands that directly manipulate AppKit/Ghostty UI state are allowed to run on the main actor.
- If adding a new socket command, default to off-main handling and require an explicit reason in code comments when main-thread execution is necessary.
## Focus policy
- Socket/CLI commands must not steal macOS app focus.View the complete source on GitHubcmux-testing
When your agent uses it
cmux testing rules for Swift Testing, test target compilation, and package/refactor validation. Use when adding or changing tests, touching package/refactor code, or deciding whether reload.sh is enough validation.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
1,153 tokensWhen the skill is activated
Reference documents
1,149 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Regression test commit policy
- Test quality policy
- Test framework
- Test target validation
- Detailed references
Files
SKILL.mdcore4,942 bytesSKILL.mdcore4,942 bytesSKILL.mdcore4,942 bytesSKILL.mdcore4,942 bytesSKILL.mdcore4,942 bytesagents/openai.yamlasset306 bytesreferences/local-vs-ci-validation.mddoc1,473 bytesreferences/regression-and-quality.mddoc1,638 bytesreferences/swift-testing-migration.mddoc1,713 bytes
Read SKILL.md
# cmux Testing
## Regression test commit policy
When adding a regression test for a bug fix, use a two-commit structure so CI proves the test catches the bug:
1. **Commit 1:** Add the failing test only (no fix). CI should go red.
2. **Commit 2:** Add the fix. CI should go green.
This makes it visible in the GitHub PR UI that the test genuinely fails without the fix.
## Test quality policy
- Do not add tests that only verify source code text, method signatures, AST fragments, or grep-style patterns.View the complete source on GitHubcmux-workspace
When your agent uses it
Work inside the current cmux workspace and terminal. Use for cmux workspace, current workspace, caller surface, panes, surfaces, socket targeting, and non-interfering cmux automation.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
2,495 tokensWhen the skill is activated
Reference documents
2,242 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Default Rule
- Non-Disruptive Automation
- Right-Side Helper Pane
- Hierarchy
- Inspect Current Context
- Workspace-Scoped Actions
- Caller Terminal
- Moving Surfaces
- Sidebar State
- Contributor Reloads
- Socket and Access
- References
- Rules
Files
../cmux-browser/SKILL.mddoc5,343 bytesSKILL.mdcore10,397 bytesSKILL.mdcore10,397 bytesSKILL.mdcore10,397 bytesSKILL.mdcore10,397 bytesSKILL.mdcore10,397 bytesSKILL.mdcore10,397 bytesSKILL.mdcore10,397 bytesSKILL.mdcore10,397 bytesSKILL.mdcore10,397 bytesSKILL.mdcore10,397 bytesSKILL.mdcore10,397 bytesSKILL.mdcore10,397 bytesSKILL.mdcore10,397 bytesSKILL.mdcore10,397 bytesSKILL.mdcore10,397 bytesSKILL.mdcore10,397 bytesSKILL.mdcore10,397 bytesSKILL.mdcore10,397 bytesSKILL.mdcore10,397 bytesSKILL.mdcore10,397 bytesagents/openai.yamlasset392 bytesreferences/commands.mddoc3,544 bytes
Read SKILL.md
# cmux Workspace
Use this skill when a task should be scoped to the cmux workspace that invoked the agent. A workspace is the sidebar tab-like unit in cmux. It contains split panes, and each pane contains one or more surfaces. A surface is the terminal or browser session the user interacts with.
## Default Rule
Scope actions to the current caller workspace unless the user explicitly asks for another workspace, another window, or global state.
Do not assume the visually focused cmux workspace is the right target. An agent can be running in one workspace while the user is looking at another. Prefer the caller environment first:
```bash
printf 'workspace=%s\nsurface=%s\nsocket=%s\n' \
"${CMUX_WORKSPACE_ID:-}" \
"${CMUX_SURFACE_ID:-}" \View the complete source on GitHubSkills included
- cmux
- cmux-architecture
- cmux-backend
- cmux-browser
- cmux-custom-sidebar
- cmux-customization
- cmux-debugging
- cmux-dev-workflow
- cmux-diagnostics
- cmux-ghostty
- cmux-keyboard-shortcuts
- cmux-localization
- cmux-markdown
- cmux-release
- cmux-settings
- cmux-shared-behavior
- cmux-socket-policy
- cmux-testing
- cmux-workspace
Repository facts
- License
- MIT
- Created
- Jun 29, 2026
- Last pushed
- Jun 29, 2026
- Forks
- 31
- Open issues
- 0
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 93 notes
ai_docs/cmux-skills/cmux/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai_docs/cmux-skills/cmux/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai_docs/cmux-skills/cmux/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai_docs/cmux-skills/cmux/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai_docs/cmux-skills/cmux-architecture/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai_docs/cmux-skills/cmux-architecture/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai_docs/cmux-skills/cmux-backend/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai_docs/cmux-skills/cmux-backend/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai_docs/cmux-skills/cmux-backend/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai_docs/cmux-skills/cmux-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai_docs/cmux-skills/cmux-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai_docs/cmux-skills/cmux-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai_docs/cmux-skills/cmux-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai_docs/cmux-skills/cmux-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai_docs/cmux-skills/cmux-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai_docs/cmux-skills/cmux-browser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai_docs/cmux-skills/cmux-custom-sidebar/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai_docs/cmux-skills/cmux-custom-sidebar/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai_docs/cmux-skills/cmux-custom-sidebar/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai_docs/cmux-skills/cmux-customization/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 3 dangerous shell commandsin 3 files: cmux-browser/references/authentication.md:121 cmux-browser/references/commands.md:44 cmux-browser/references/session-management.md:86
- 78 network referencesin 15 files: cmux-browser/references/session-management.md:19 ai_docs/cmux-skills/cmux-browser/SKILL.md:20 cmux-customization/references/examples.md:107 and 12 more
- No hidden or obfuscated text
- No instruction overrides
- 5 executable scriptsin 5 files: cmux-browser/templates/authenticated-session.sh:1 cmux-browser/templates/capture-workflow.sh:1 cmux-browser/templates/form-automation.sh:1 and 2 more
- 6 references to secretsin 4 files: cmux-backend/SKILL.md:28 cmux-browser/references/authentication.md:83 cmux-browser/references/commands.md:72 and 1 more
- No requests to vote in Hot
Show all 92 signals by file
ai_docs/cmux-skills/cmux-backend/SKILL.md
ai_docs/cmux-skills/cmux-browser/SKILL.md
- Network accessline 20
cmux --json browser open https://example.com - Network accessline 20
cmux --json browser open https://example.com - Network accessline 20
cmux --json browser open https://example.com - Network accessline 37
# open routed to a specific topology target cmux browser open https://example.com --workspace workspace:2 --window window:1 --json - Network accessline 37
# open routed to a specific topology target cmux browser open https://example.com --workspace workspace:2 --window window:1 --json - Network accessline 37
# open routed to a specific topology target cmux browser open https://example.com --workspace workspace:2 --window window:1 --json - Network accessline 38
cmux browser open https://example.com --workspace workspace:2 --window window:1 --json - Network accessline 38
cmux browser open https://example.com --workspace workspace:2 --window window:1 --json - Network accessline 38
cmux browser open https://example.com --workspace workspace:2 --window window:1 --json - Network accessline 63
cmux --json browser open https://example.com/signup - Network accessline 63
cmux --json browser open https://example.com/signup - Network accessline 63
cmux --json browser open https://example.com/signup
ai_docs/cmux-skills/cmux-browser/references/authentication.md
- Network accessline 21
cmux browser open https://app.example.com/login --json - Network accessline 46
cmux browser open https://app.example.com --json - Network accessline 47
cmux browser surface:8 state load ./auth-state.json cmux browser surface:8 goto https://app.example.com/dashboard cmux browser surface:8 snapshot --interactive - Network accessline 48
cmux browser surface:8 goto https://app.example.com/dashboard - Network accessline 55
cmux browser open https://app.example.com/auth/google --json - Network accessline 69
cmux browser open https://app.example.com/login --json - Network accessline 83
[Credential-related source omitted] - Access to secretsline 83
[Credential-related source omitted] - Network accessline 84
cmux browser surface:7 goto https://app.example.com/dashboard - Network accessline 100
cmux browser "$SURFACE" goto https://app.example.com/dashboard - Access to secretsline 120
[Credential-related source omitted] - Dangerous shell operationline 121
rm -f ./auth-state.json
ai_docs/cmux-skills/cmux-browser/references/commands.md
ai_docs/cmux-skills/cmux-browser/references/proxy-support.md
- Network accessline 33
cmux browser open https://httpbin.org/ip --json
ai_docs/cmux-skills/cmux-browser/references/session-management.md
- Network accessline 19
# session A cmux browser open https://app.example.com/login --json - Network accessline 20
cmux browser open https://app.example.com/login --json - Network accessline 23
# session B cmux browser open https://example.com --json - Network accessline 24
cmux browser open https://example.com --json - Network accessline 50
cmux browser surface:8 state load /tmp/auth-state.json cmux browser surface:8 goto https://app.example.com/dashboard - Network accessline 51
cmux browser surface:8 goto https://app.example.com/dashboard - Network accessline 59
cmux browser open https://app.example.com/login --json - Network accessline 63
cmux browser open https://app.example.com --json - Network accessline 64
# assume surface:8 cmux browser surface:8 state load /tmp/auth.json cmux browser surface:8 goto https://app.example.com/dashboard - Network accessline 66
cmux browser surface:8 goto https://app.example.com/dashboard - Network accessline 72
cmux browser open https://site-a.example --json - Network accessline 73
cmux browser open https://site-b.example --json - Network accessline 74
cmux browser open https://site-c.example --json - Dangerous shell operationline 86
rm -f /tmp/auth-state.json
ai_docs/cmux-skills/cmux-browser/templates/authenticated-session.sh
- Executable scriptline 1
#!/usr/bin/env bash - Network accessline 4
SURFACE="${1:-surface:1}" STATE_FILE="${2:-./auth-state.json}" DASHBOARD_URL="${3:-https://app.example.com/dashboard}" - Network accessline 6
DASHBOARD_URL="${3:-https://app.example.com/dashboard}" - Network accessline 12
cmux browser "$SURFACE" goto "$DASHBOARD_URL"
ai_docs/cmux-skills/cmux-browser/templates/capture-workflow.sh
- Executable scriptline 1
#!/usr/bin/env bash
ai_docs/cmux-skills/cmux-browser/templates/form-automation.sh
ai_docs/cmux-skills/cmux-custom-sidebar/SKILL.md
- Network accessline 17
cmux docs sidebars curl -fsSL https://raw.githubusercontent.com/manaflow-ai/cmux/main/docs/custom-sidebars.md - Network accessline 18
curl -fsSL https://raw.githubusercontent.com/manaflow-ai/cmux/main/docs/custom-sidebars.md - Network accessline 79
A button or `.onTapGesture` body calls `cmux("<method>", param: value)`, dispatched through the same surface as the `cmux` CLI. Common methods: `workspace.select` (`workspace_id`), `surface.focus` (`surface_id`), `workspace.reorder` (`works
ai_docs/cmux-skills/cmux-customization/SKILL.md
- Network accessline 167
"children": [ { "pane": { "surfaces": [{ "type": "terminal", "command": "bun dev" }] } }, { "pane": { "surfaces": [{ "type": "browser", "url": "http://localhost:3000" }] } } - Network accessline 168
{ "pane": { "surfaces": [{ "type": "terminal", "command": "bun dev" }] } }, { "pane": { "surfaces": [{ "type": "browser", "url": "http://localhost:3000" }] } } ] - Network accessline 169
{ "pane": { "surfaces": [{ "type": "browser", "url": "http://localhost:3000" }] } }
ai_docs/cmux-skills/cmux-customization/references/examples.md
- Network accessline 107
"pane": { "surfaces": [ { "type": "browser", "name": "Preview", "url": "http://localhost:3000" } - Network accessline 108
"surfaces": [ { "type": "browser", "name": "Preview", "url": "http://localhost:3000" } ] - Network accessline 109
{ "type": "browser", "name": "Preview", "url": "http://localhost:3000" } - Network accessline 157
"pane": { "surfaces": [ { "type": "browser", "name": "Preview", "url": "http://localhost:3000" } - Network accessline 158
"surfaces": [ { "type": "browser", "name": "Preview", "url": "http://localhost:3000" } ] - Network accessline 159
{ "type": "browser", "name": "Preview", "url": "http://localhost:3000" } - Network accessline 197
"pane": { "surfaces": [ { "type": "browser", "name": "Pull Request", "url": "https://github.com/owner/repo/pulls" } - Network accessline 198
"surfaces": [ { "type": "browser", "name": "Pull Request", "url": "https://github.com/owner/repo/pulls" } ] - Network accessline 199
{ "type": "browser", "name": "Pull Request", "url": "https://github.com/owner/repo/pulls" } - Network accessline 254
"pane": { "surfaces": [ { "type": "browser", "name": "Docs Preview", "url": "http://localhost:3000/docs" } - Network accessline 255
"surfaces": [ { "type": "browser", "name": "Docs Preview", "url": "http://localhost:3000/docs" } ] - Network accessline 256
{ "type": "browser", "name": "Docs Preview", "url": "http://localhost:3000/docs" }
ai_docs/cmux-skills/cmux-diagnostics/scripts/cmux-diagnostics
- Executable scriptline 1
#!/usr/bin/env bash
ai_docs/cmux-skills/cmux-settings/SKILL.md
- Network accessline 10
Schema: `https://raw.githubusercontent.com/manaflow-ai/cmux/main/web/data/cmux.schema.json`. The authoritative path list lives in `Sources/CmuxSettingsJSONPathSupport.swift` in the cmux checkout, and the installed skill includes a generated - Network accessline 10
Schema: `https://raw.githubusercontent.com/manaflow-ai/cmux/main/web/data/cmux.schema.json`. The authoritative path list lives in `Sources/CmuxSettingsJSONPathSupport.swift` in the cmux checkout, and the installed skill includes a generated
ai_docs/cmux-skills/cmux-settings/references/all-keys.md
- Network accessline 3
Auto-generated from `web/data/cmux.schema.json`. For the rendered docs, see `https://cmux.com/docs/configuration`.
ai_docs/cmux-skills/cmux-settings/scripts/cmux-settings
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 41
DEFAULT_PATH = Path.home() / ".config" / "cmux" / "cmux.json" SCHEMA_URL = ( "https://raw.githubusercontent.com/manaflow-ai/cmux/main/web/data/cmux.schema.json" - Network accessline 42
SCHEMA_URL = ( "https://raw.githubusercontent.com/manaflow-ai/cmux/main/web/data/cmux.schema.json" ) - Network accessline 43
"https://raw.githubusercontent.com/manaflow-ai/cmux/main/web/data/cmux.schema.json" - Access to secretsline 386
[Credential-related source omitted]
ai_docs/cmux-skills/cmux-workspace/SKILL.md
- Network accessline 41
# pane and content in one call, no follow-up needed cmux new-pane --workspace "${CMUX_WORKSPACE_ID}" --type browser --direction right --url "http://127.0.0.1:8765" - Network accessline 41
# pane and content in one call, no follow-up needed cmux new-pane --workspace "${CMUX_WORKSPACE_ID}" --type browser --direction right --url "http://127.0.0.1:8765" - Network accessline 42
cmux new-pane --workspace "${CMUX_WORKSPACE_ID}" --type browser --direction right --url "http://127.0.0.1:8765" - Network accessline 42
cmux new-pane --workspace "${CMUX_WORKSPACE_ID}" --type browser --direction right --url "http://127.0.0.1:8765" - Network accessline 48
Pass `--focus false` whenever the verb supports it. `move-surface --focus false` preserves the user's current attention. Other commands may grow the same flag over time (https://github.com/manaflow-ai/cmux/issues/1418, https://github.com/ma - Network accessline 48
Pass `--focus false` whenever the verb supports it. `move-surface --focus false` preserves the user's current attention. Other commands may grow the same flag over time (https://github.com/manaflow-ai/cmux/issues/1418, https://github.com/ma - Network accessline 162
Known papercut: `drag-surface-to-split` currently routes through V1 and resolves the workspace via UI focus, so it can fail with `ERROR: Surface not found` when the caller's workspace is not the visually focused one. Tracked at https://gith - Network accessline 162
Known papercut: `drag-surface-to-split` currently routes through V1 and resolves the workspace via UI focus, so it can fail with `ERROR: Surface not found` when the caller's workspace is not the visually focused one. Tracked at https://gith
ai_docs/cmux-skills/cmux-workspace/references/commands.md
- Network accessline 45
cmux new-split down --workspace "$CMUX_WORKSPACE_ID" --surface "$CMUX_SURFACE_ID" cmux new-pane --workspace "$CMUX_WORKSPACE_ID" --type terminal --direction right cmux new-pane --workspace "$CMUX_WORKSPACE_ID" --type browser --url http://lo - Network accessline 46
cmux new-pane --workspace "$CMUX_WORKSPACE_ID" --type terminal --direction right cmux new-pane --workspace "$CMUX_WORKSPACE_ID" --type browser --url http://localhost:3000 cmux new-surface --workspace "$CMUX_WORKSPACE_ID" --type terminal --p - Network accessline 47
cmux new-pane --workspace "$CMUX_WORKSPACE_ID" --type browser --url http://localhost:3000 - Network accessline 49
cmux new-surface --workspace "$CMUX_WORKSPACE_ID" --type browser --pane pane:1 --url http://localhost:3000
ai_docs/cmux-skills/cmux/references/panes-surfaces.md
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 92 facts
- Access to secrets in prose of the SKILL.mdcmux-backend/SKILL.md:28Low confidence
- Access to secrets in prose of the SKILL.mdcmux-backend/SKILL.md:29Low confidence
- Network access in code of the SKILL.mdai_docs/cmux-skills/cmux-browser/SKILL.md:20High confidence
- Network access in code of the SKILL.mdcmux-browser/SKILL.md:20High confidence
- Network access in code of the SKILL.mdai_docs/cmux-skills/cmux-browser/SKILL.md:20High confidence
- Network access in code of the SKILL.mdai_docs/cmux-skills/cmux-browser/SKILL.md:37High confidence
- Network access in code of the SKILL.mdcmux-browser/SKILL.md:37High confidence
- Network access in code of the SKILL.mdai_docs/cmux-skills/cmux-browser/SKILL.md:37High confidence
- Network access in code of the SKILL.mdai_docs/cmux-skills/cmux-browser/SKILL.md:38High confidence
- Network access in code of the SKILL.mdcmux-browser/SKILL.md:38High confidence
- Network access in code of the SKILL.mdai_docs/cmux-skills/cmux-browser/SKILL.md:38High confidence
- Network access in code of the SKILL.mdai_docs/cmux-skills/cmux-browser/SKILL.md:63High confidence
- Network access in code of the SKILL.mdcmux-browser/SKILL.md:63High confidence
- Network access in code of the SKILL.mdai_docs/cmux-skills/cmux-browser/SKILL.md:63High confidence
- Network access in code of documentationcmux-browser/references/authentication.md:21Low confidence
- Network access in code of documentationcmux-browser/references/authentication.md:46Low confidence
- Network access in code of documentationcmux-browser/references/authentication.md:47Low confidence
- Network access in code of documentationcmux-browser/references/authentication.md:48Low confidence
- Network access in code of documentationcmux-browser/references/authentication.md:55Low confidence
- Network access in code of documentationcmux-browser/references/authentication.md:69Low confidence
- Network access in code of documentationcmux-browser/references/authentication.md:83Low confidence
- Access to secrets in code of documentationcmux-browser/references/authentication.md:83Low confidence
- Network access in code of documentationcmux-browser/references/authentication.md:84Low confidence
- Network access in code of documentationcmux-browser/references/authentication.md:100Low confidence
- Access to secrets in code of documentationcmux-browser/references/authentication.md:120Low confidence
- Dangerous shell operation in code of documentationcmux-browser/references/authentication.md:121Low confidence
- Dangerous shell operation in code of documentationcmux-browser/references/commands.md:44Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored valuecmux-browser/references/commands.md:72Low confidence
- Network access in code of documentationcmux-browser/references/proxy-support.md:33Low confidence
- Network access in code of documentationcmux-browser/references/session-management.md:19Low confidence
- Network access in code of documentationcmux-browser/references/session-management.md:20Low confidence
- Network access in code of documentationcmux-browser/references/session-management.md:23Low confidence
- Network access in code of documentationcmux-browser/references/session-management.md:24Low confidence
- Network access in code of documentationcmux-browser/references/session-management.md:50Low confidence
- Network access in code of documentationcmux-browser/references/session-management.md:51Low confidence
- Network access in code of documentationcmux-browser/references/session-management.md:59Low confidence
- Network access in code of documentationcmux-browser/references/session-management.md:63Low confidence
- Network access in code of documentationcmux-browser/references/session-management.md:64Low confidence
- Network access in code of documentationcmux-browser/references/session-management.md:66Low confidence
- Network access in code of documentationcmux-browser/references/session-management.md:72Low confidence
- Network access in code of documentationcmux-browser/references/session-management.md:73Low confidence
- Network access in code of documentationcmux-browser/references/session-management.md:74Low confidence
- Dangerous shell operation in code of documentationcmux-browser/references/session-management.md:86Low confidence
- Executable script in code of a file that runscmux-browser/templates/authenticated-session.sh:1High confidence
- Network access in code of a file that runscmux-browser/templates/authenticated-session.sh:4High confidence
- Network access in code of a file that runscmux-browser/templates/authenticated-session.sh:6High confidence
- Network access in code of a file that runscmux-browser/templates/authenticated-session.sh:12High confidence
- Executable script in code of a file that runscmux-browser/templates/capture-workflow.sh:1High confidence
- Executable script in code of a file that runscmux-browser/templates/form-automation.sh:1High confidence
- Network access in code of a file that runscmux-browser/templates/form-automation.sh:4High confidence
and 42 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Path .claude/agents/build-be.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md ai_docs/cmux-skills/cmux/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md ai_docs/cmux-skills/cmux/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md ai_docs/cmux-skills/cmux/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md ai_docs/cmux-skills/cmux/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md ai_docs/cmux-skills/cmux/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.