Not in the top 1,000 by GitHub stars

LearnPrompt/partner-skill

搭子.skill / Partner：Claude Code 负责规划、润色和审查，Codex 负责实现、监控和验收。Same-session receipts prove no wasted Claude cold starts.

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

`SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

139df5a4feb4 → 139df5a4feb4

Compare on GitHub

`idea-king/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

139df5a4feb4 → 139df5a4feb4

Compare on GitHub

View on GitHub Add to my skills

Verified commit 139df5a4feb4bf878f8972daa4542851eb83d0fd

67GitHub stars

0stars in 7 days

2skills in this repository

0commits in 30 days

Heat

0.3

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

partner-skill /
idea-king idea-king

How it works

Choose a skill

partner-skill

When your agent uses it

搭子.skill / Partner — two-direction cost-split workflow between Claude Code and Codex. Direction A (Codex-driven): Codex orchestrates and implements; Claude Code plans (/goal), polishes UI/interaction, and runs final /codex:review in one reused session. Direction B (Claude-driven): Claude plans and splits the work, runs the idea-king adversarial gate, delegates to Codex background jobs, monitors, and full-reviews before accepting. Use on "搭子" / "双向搭子" / "搭子，恢复" (resume from .partner/), "搭子，配置" (first-run setup wizard), "搭子，试跑" (identity tryout report), 分工给 codex / 让 codex 做 / codex 后台跑 / Claude 计划 Codex 实现 / 让 Claude skip 做完, or any request to split coding work between Claude Code and Codex to save quota. Not for ordinary code review without Claude Code; do not trigger on the bare English word "partner" in unrelated contexts.

What it loads into context

Frontmatter

242 tokens

Always available to the agent

SKILL.md

2,520 tokens

When the skill is activated

Reference documents

50,702 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Overview
Host Detection
Configuration
Tool Location
Routing Rules
Bounded Claude Planning
Validation Gate
Monitoring
Output Contract

Scripts executed separately

install.sh
scripts/check-claude-cli.sh
scripts/check-readme-parity.py
scripts/check-skill-repo.sh
scripts/delegate-codex.sh
scripts/goal-sync.py
scripts/make-handoff.sh
scripts/make-receipt.py
scripts/partner-config.py
scripts/partner-setup-ui.py
scripts/partner-setup.py
scripts/partner_runtime.py
scripts/run-claude-plan.py
scripts/run-test-prompts.py
scripts/sandbox-matrix.sh
scripts/session-snapshot.sh
scripts/showcase-cost-ledger.py
scripts/validate-receipt.py
tests/test_delegate_role.py
tests/test_delegate_sandbox.py
tests/test_goal_sync.py
tests/test_partner_config.py
tests/test_partner_setup.py
tests/test_partner_setup_ui.py
tests/test_run_claude_plan.py

Files

.github/workflows/checks.ymlasset2,003 bytes
.gitignoreasset58 bytes
CHANGELOG.mddoc7,430 bytes
LICENSEasset1,068 bytes
README.en.mddoc23,040 bytes
README.mddoc21,659 bytes
SKILL.mdcore11,037 bytes
SKILL.mdcore11,037 bytes
SKILL.mdcore11,037 bytes
SKILL.mdcore11,037 bytes
SKILL.mdcore11,037 bytes
SKILL.mdcore11,037 bytes
SKILL.mdcore11,037 bytes
assets/config-switch-demo.gifasset3,627,999 bytes
assets/config-switch-demo.mp4asset1,362,736 bytes
assets/showcase-idea-king.gifasset148,890 bytes
assets/showcase.gifasset190,627 bytes
assets/v2.0.1-conversation-cost-receipt.pngasset457,994 bytes
docs/CHANGES.mddoc14,223 bytes
docs/TEST.mddoc13,116 bytes
docs/config-schema.mddoc6,958 bytes
docs/receipt-schema.jsonasset4,568 bytes
docs/releases/v2.0.0.mddoc2,355 bytes
docs/releases/v2.0.1.mddoc3,522 bytes
docs/showcase-cost-model.mddoc4,210 bytes
docs/v1.5-dual-host-acceptance.mddoc8,042 bytes
examples/session-receipt.mddoc877 bytes
examples/showcase-cost-ledger.jsonasset2,582 bytes
examples/v2.0.0-conversation-cost-receipt.mddoc3,004 bytes
examples/v2.0.1-conversation-cost-receipt.htmlasset21,169 bytes
examples/v2.0.1-conversation-cost-receipt.mddoc5,906 bytes
install.shruns7,554 bytes
red-skill-submission.mddoc12,913 bytes
references/bounded-planning.mddoc5,240 bytes
references/claude-driven.mddoc13,093 bytes
references/codex-driven.mddoc7,126 bytes
references/darwin-ratchet.mddoc2,020 bytes
references/fable5-principles.mddoc5,823 bytes
references/failure-playbook.mddoc5,336 bytes
references/goal-template.mddoc3,686 bytes
references/goal-to-pr.mddoc6,452 bytes
references/handoff-template.mddoc5,899 bytes
references/memory-protocol.mddoc2,150 bytes
references/monitoring.mddoc5,888 bytes
references/scenarios.mddoc3,193 bytes
references/setup.mddoc6,617 bytes
references/tryout.mddoc3,961 bytes
scripts/check-claude-cli.shruns2,010 bytes
scripts/check-readme-parity.pyruns7,158 bytes
scripts/check-skill-repo.shruns10,610 bytes
scripts/delegate-codex.shruns20,896 bytes
scripts/goal-sync.pyruns4,009 bytes
scripts/make-handoff.shruns3,716 bytes
scripts/make-receipt.pyruns4,879 bytes
scripts/partner-config.pyruns33,156 bytes
scripts/partner-setup-ui.pyruns77,653 bytes
scripts/partner-setup.pyruns52,052 bytes
scripts/partner_runtime.pyruns748 bytes
scripts/run-claude-plan.pyruns43,731 bytes
scripts/run-test-prompts.pyruns5,396 bytes
scripts/sandbox-matrix.shruns8,474 bytes
scripts/session-snapshot.shruns2,309 bytes
scripts/showcase-cost-ledger.pyruns5,695 bytes
scripts/validate-receipt.pyruns8,742 bytes
test-prompts.jsonasset27,437 bytes
tests/test_delegate_role.pyruns9,094 bytes
tests/test_delegate_sandbox.pyruns7,563 bytes
tests/test_goal_sync.pyruns3,458 bytes
tests/test_partner_config.pyruns23,843 bytes
tests/test_partner_setup.pyruns29,820 bytes
tests/test_partner_setup_ui.pyruns11,743 bytes
tests/test_run_claude_plan.pyruns37,366 bytes

Read SKILL.md


# 搭子.skill (Partner)

> 我的 Claude Code 和 Codex 天下第一好。

## Overview

Use this skill to run a two-agent coding workflow: Claude Code is the high-value planning, polish, and review agent; Codex is the outer orchestrator and main implementer. Keep Claude Code usage focused because it may be billed through API.

Prefer one long-lived Claude Code session for small and medium tasks: ask Claude for the plan, let Codex implement, then return the diff summary and key files to the same Claude session for UI/interaction polish and final `/codex:review`. This avoids paying Claude to rebuild the same project context and gives Claude enough continuity to improve the work.

Partner is not a delegation excuse. The user remains the owner, Codex remains accountable for repository evidence, and Claude Code is treated as a high-value collaborator whose output must be verified.

## Host Detection

View the complete source on GitHub

idea-king

When your agent uses it

点子王 (Idea King) — reason from first principles & run adversarial review. A thinking partner for the Partner (搭子) workflow and for standalone use. Use when the user says "点子王", "idea king", "第一性原理", "从第一性原理出发", "奥卡姆剃刀", "墨菲定律", "科斯定理", "对抗式审查", "挑战这个方案", "attack this plan", "盘问", "grill this plan", or when a plan / architecture / work split needs to be stress-tested before execution. Partner Direction B calls this skill on every division-of-labor plan before delegating.

What it loads into context

Frontmatter

154 tokens

Always available to the agent

SKILL.md

2,113 tokens

When the skill is activated

Reference documents

2,970 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Pre-Verdict Protocol — 逐题追问 (Clarify to 95%)
Mode 1 — First-Principles Decomposition (第一性原理拆解)
Mode 2 — Adversarial Review (对抗式审查)
Mode 3 — Grill (盘问)
Output Format (fixed, all modes)
Rules

Files

README.mddoc3,049 bytes
SKILL.mdcore9,040 bytes
codex-prompt.mddoc4,819 bytes
references/adversarial-checklist.mddoc4,344 bytes

Read SKILL.md


# 点子王 (Idea King)

Core stance: 从第一性原理出发 & 开启对抗式审查。You are not here to be
agreeable. You are here to find where the idea is wrong before reality does.

Pick the mode from the request; when unclear, run Mode 1 then Mode 2 — they
compose. Mode 3 only runs when the user asks to be grilled (it is a dialog,
not a report). Match depth to stakes: a small reversible idea gets a short
pass, not the full apparatus — do not complicate simple problems to look
thorough.

## Pre-Verdict Protocol — 逐题追问 (Clarify to 95%)

Default gate for every mode: do not issue a verdict on a need you only 95%

View the complete source on GitHub

Skills included

partner-skill
idea-king

Repository facts

License: MIT
Created: Jun 23, 2026
Last pushed: Sep 9, 2026
Forks: 8
Open issues: 0
Project activity: Active

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 6, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 6 notes

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
7 dangerous shell commandsin 4 files: scripts/check-skill-repo.sh:8 install.sh:192 scripts/run-test-prompts.py:36 and 1 more
59 network referencesin 9 files: idea-king/README.md:46 README.en.md:9 README.md:9 and 6 more
No hidden or obfuscated text
2 instruction override signalsin 2 files: docs/CHANGES.md:34 references/codex-driven.md:77
25 executable scriptsin 25 files: install.sh:1 scripts/check-claude-cli.sh:1 scripts/check-readme-parity.py:1 and 22 more
24 references to secretsin 13 files: tests/test_run_claude_plan.py:44 tests/test_partner_setup.py:44 scripts/run-claude-plan.py:1181 and 10 more
No requests to vote in Hot

Show all 117 signals by file

`README.en.md`

Network accessline 9

[![Agent Skills](https://img.shields.io/badge/Agent%20Skills-partner--skill-blueviolet)](SKILL.md)

Network accessline 10

[![Version: 2.0.1](https://img.shields.io/badge/version-2.0.1-ef6f4f)](CHANGELOG.md)

Network accessline 11

[![GitHub stars](https://img.shields.io/github/stars/LearnPrompt/partner-skill?style=flat-square&color=f5c542)](https://github.com/LearnPrompt/partner-skill/stargazers)

Network accessline 12

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)

Network accessline 33

Please install Partner Skill: https://github.com/LearnPrompt/partner-skill

Network accessline 39

git clone https://github.com/LearnPrompt/partner-skill.git

Network accessline 338

**更多好用 Skill · More Skills** → [learnprompt.pro/skills](https://learnprompt.pro/skills/)

Network accessline 340

[鲁班·Skill打磨](https://github.com/LearnPrompt/luban-skill) · [庖丁·博主蒸馏](https://github.com/LearnPrompt/paoding-skill) · [蔡伦·对话造纸](https://github.com/LearnPrompt/cailun-skill) · [阿福·LLM Todo](https://github.com/LearnPrompt/afu-llm-todo) · [愚公·L

Network accessline 342

[淘金小镇·ClawHub日榜](https://github.com/LearnPrompt/skillrush-town) · [Irasutoya·正文配图](https://github.com/LearnPrompt/carl-irasutoya-illustrations) · [Humanize PPT·演讲系统](https://github.com/LearnPrompt/humanize-ppt) · [CC Harness·六件套](https://gi

Network accessline 344

<sub>**[LearnPrompt](https://github.com/LearnPrompt) 出品** · 公众号「卡尔的AI沃茨」 · [X @aiwarts](https://x.com/aiwarts)</sub>

Network accessline 346

<sub>Acknowledgment: the done_when / anti-Goodhart / imperative-authorization vocabulary in `references/goal-to-pr.md` draws on [愚公·Loop工程](https://github.com/LearnPrompt/loop-engineering)'s goal-forging.md and guardrails.md (vocabulary and

`README.md`

Network accessline 9

[![Agent Skills](https://img.shields.io/badge/Agent%20Skills-partner--skill-blueviolet)](SKILL.md)

Network accessline 10

[![Version: 2.0.1](https://img.shields.io/badge/version-2.0.1-ef6f4f)](CHANGELOG.md)

Network accessline 11

[![GitHub stars](https://img.shields.io/github/stars/LearnPrompt/partner-skill?style=flat-square&color=f5c542)](https://github.com/LearnPrompt/partner-skill/stargazers)

Network accessline 12

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)

Network accessline 33

请安装搭子.skill：https://github.com/LearnPrompt/partner-skill

Network accessline 39

git clone https://github.com/LearnPrompt/partner-skill.git

Network accessline 337

**更多好用 Skill · More Skills** → [learnprompt.pro/skills](https://learnprompt.pro/skills/)

Network accessline 339

[鲁班·Skill打磨](https://github.com/LearnPrompt/luban-skill) · [庖丁·博主蒸馏](https://github.com/LearnPrompt/paoding-skill) · [蔡伦·对话造纸](https://github.com/LearnPrompt/cailun-skill) · [阿福·LLM Todo](https://github.com/LearnPrompt/afu-llm-todo) · [愚公·L

Network accessline 341

[淘金小镇·ClawHub日榜](https://github.com/LearnPrompt/skillrush-town) · [Irasutoya·正文配图](https://github.com/LearnPrompt/carl-irasutoya-illustrations) · [Humanize PPT·演讲系统](https://github.com/LearnPrompt/humanize-ppt) · [CC Harness·六件套](https://gi

Network accessline 343

<sub>**[LearnPrompt](https://github.com/LearnPrompt) 出品** · 公众号「卡尔的AI沃茨」 · [X @aiwarts](https://x.com/aiwarts)</sub>

Network accessline 345

<sub>致谢：`references/goal-to-pr.md` 的 done_when / anti-Goodhart / 祈使句授权法词汇，参考了 [愚公·Loop工程](https://github.com/LearnPrompt/loop-engineering) 的 goal-forging.md 与 guardrails.md（只借词汇与不变量，不搬 YAML 格式与仪式）。</sub>

`docs/CHANGES.md`

Instruction override signalline 34

原版把用户说 "skip" 直接映射为启动 `--dangerously-skip-permissions`。现版本规定：只有当 skip 明确指权限模式时才升级权限；当 skip 可能指"跳过某个步骤"（如"跳过 polish"）时，必须先问一句确认。`test-prompts.json` 的 `explicit-skip-ui-polish` 用例同步更新。

`docs/TEST.md`

Network accessline 7

目标仓库：`https://github.com/LearnPrompt/partner-skill`

Network accessline 22

git clone --recurse-submodules https://github.com/LearnPrompt/partner-skill.git partner-skill

Network accessline 29

当前分支：main 当前提交：764f4bbcb1953bf4e6a7fd935b3f7d73f27b9b40 远程地址：https://github.com/LearnPrompt/partner-skill.git

Network accessline 30

当前提交：764f4bbcb1953bf4e6a7fd935b3f7d73f27b9b40 远程地址：https://github.com/LearnPrompt/partner-skill.git 仓库大小：约 1.9M

Network accessline 31

远程地址：https://github.com/LearnPrompt/partner-skill.git

`docs/receipt-schema.json`

Network accessline 1

{   "$schema": "https://json-schema.org/draft/2020-12/schema",

Network accessline 2

"$schema": "https://json-schema.org/draft/2020-12/schema",

`docs/v1.5-dual-host-acceptance.md`

Network accessline 7

- 仓库：`https://github.com/LearnPrompt/partner-skill`

Network accessline 88

请从 https://github.com/LearnPrompt/partner-skill/tree/feat/v1.5-dual-host 安装搭子.skill。把我当成第一次使用的小白；安装完成后告诉我下一句只要说什么，不要让我手敲配置命令。

Network accessline 119

请从 https://github.com/LearnPrompt/partner-skill/tree/feat/v1.5-dual-host 安装搭子.skill。这里已经由 Codex 配过一次；请保留它的配置，把我当成第一次使用 Claude Code 这一侧的小白。

`examples/v2.0.1-conversation-cost-receipt.md`

Network accessline 106

- implementation commit: `3c27a35` - README/showcase commit: `304b21a` - PR: <https://github.com/LearnPrompt/partner-skill/pull/4>

Network accessline 107

- README/showcase commit: `304b21a` - PR: <https://github.com/LearnPrompt/partner-skill/pull/4> - local tests: 102/102 passed

Network accessline 108

- PR: <https://github.com/LearnPrompt/partner-skill/pull/4>

`idea-king/README.md`

Network accessline 46

修辞数字、一次一问不约束问什么）。 - 奥卡姆剃刀 — William of Ockham，如无必要勿增实体   （[Occam's razor](https://en.wikipedia.org/wiki/Occam%27s_razor)）

Network accessline 47

- 奥卡姆剃刀 — William of Ockham，如无必要勿增实体   （[Occam's razor](https://en.wikipedia.org/wiki/Occam%27s_razor)）   → Mode 1 step 5 孪生检查。

Network accessline 48

（[Occam's razor](https://en.wikipedia.org/wiki/Occam%27s_razor)）

Network accessline 49

→ Mode 1 step 5 孪生检查。 - 墨菲定律 — 凡是可能出错的，一定会出错   （[Murphy's law](https://en.wikipedia.org/wiki/Murphy%27s_law)）

Network accessline 50

- 墨菲定律 — 凡是可能出错的，一定会出错   （[Murphy's law](https://en.wikipedia.org/wiki/Murphy%27s_law)）   → Mode 2 证伪实验设计与 happy-path 验收攻击。

Network accessline 51

（[Murphy's law](https://en.wikipedia.org/wiki/Murphy%27s_law)）

Network accessline 53

- 科斯定理 — Ronald Coase,《企业的性质》(1937) /《社会成本问题》(1960)，   交易成本决定边界   （[Coase theorem](https://en.wikipedia.org/wiki/Coase_theorem)）

Network accessline 54

交易成本决定边界   （[Coase theorem](https://en.wikipedia.org/wiki/Coase_theorem)）   → 工作拆分攻击与 Integration Cost 清单。

Network accessline 55

（[Coase theorem](https://en.wikipedia.org/wiki/Coase_theorem)）

Network accessline 56

→ 工作拆分攻击与 Integration Cost 清单。 - 可证伪性 — Karl Popper   （[Falsifiability](https://en.wikipedia.org/wiki/Falsifiability)）

Network accessline 57

- 可证伪性 — Karl Popper   （[Falsifiability](https://en.wikipedia.org/wiki/Falsifiability)）   → 每个攻击点强制配一个最便宜的证伪实验。

Network accessline 58

（[Falsifiability](https://en.wikipedia.org/wiki/Falsifiability)）

`install.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```

Dangerous shell operationline 192

rm -rf "$old_backup" # risk-ok: prunes only our own timestamped backups beyond BACKUP_KEEP

Dangerous shell operationline 216

rm -rf "$old_backup" # risk-ok: prunes only our own timestamped backups beyond BACKUP_KEEP

`references/codex-driven.md`

Instruction override signalline 77

- For skip mode, start Claude Code with `claude --permission-mode bypassPermissions --name <task-name>` or `claude --dangerously-skip-permissions --name <task-name>`.

`scripts/check-claude-cli.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```

`scripts/check-readme-parity.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/check-skill-repo.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```
Dangerous shell operationline 8
```
trap 'rm -f "$SCAN_TMP"' EXIT
```

Dangerous shell operationline 159

if jq -e '[.[] | (.expected_behavior[]?, .prompt)] | map(select(test("git reset --hard|rm -rf|force push|--force"))) | length == 0' test-prompts.json >/dev/null; then

Access to secretsline 284
```
[Credential-related source omitted]
```

Dangerous shell operationline 302

if grep -RInE 'git reset --hard|rm -rf|force push|--force' \

`scripts/delegate-codex.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```

`scripts/goal-sync.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/make-handoff.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```
Access to secretsline 107
```
[Credential-related source omitted]
```

`scripts/make-receipt.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/partner-config.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 458
```
[Credential-related source omitted]
```

`scripts/partner-setup-ui.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

Network accessline 1279

}     async function api(path, body) {       const response = await fetch(path, {

Network accessline 1280

async function api(path, body) {       const response = await fetch(path, {         method: body ? 'POST' : 'GET',

Network accessline 1281
```
const response = await fetch(path, {
```
Access to secretsline 1486
```
[Credential-related source omitted]
```
Network accessline 1502
```
[Credential-related source omitted]
```
Network accessline 1503
```
[Credential-related source omitted]
```
Network accessline 1504
```
[Credential-related source omitted]
```

`scripts/partner-setup.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 1117
```
[Credential-related source omitted]
```

`scripts/partner_runtime.py`

Executable scriptline 1
```
Executable file
```

`scripts/run-claude-plan.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 1181
```
[Credential-related source omitted]
```
Access to secretsline 1186
```
[Credential-related source omitted]
```
Access to secretsline 1199
```
[Credential-related source omitted]
```

`scripts/run-test-prompts.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

Dangerous shell operationline 36

RISKY = re.compile(r"git reset --hard|rm -rf|force push|--force")  # risk-ok: detection pattern, not a command

Access to secretsline 133
```
[Credential-related source omitted]
```

`scripts/sandbox-matrix.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```

Dangerous shell operationline 19

"$TMP_BASE"/partner-sandbox.*) rm -rf -- "$scratch" ;;

`scripts/session-snapshot.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```

`scripts/showcase-cost-ledger.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 77
```
[Credential-related source omitted]
```

`scripts/validate-receipt.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`tests/test_delegate_role.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 40
```
[Credential-related source omitted]
```

`tests/test_delegate_sandbox.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 42
```
[Credential-related source omitted]
```

`tests/test_goal_sync.py`

Executable scriptline 1
```
Executable file
```

`tests/test_partner_config.py`

Executable scriptline 1
```
Executable file
```

`tests/test_partner_setup.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 44
```
[Credential-related source omitted]
```
Access to secretsline 53
```
[Credential-related source omitted]
```

Network accessline 618

"PATH": "/usr/bin",             "HOME": "/home/carl",             "ANTHROPIC_BASE_URL": "https://poisoned.example",

Network accessline 619
```
[Credential-related source omitted]
```

Network accessline 620

"ANTHROPIC_BASE_URL": "https://poisoned.example",

Access to secretsline 621
```
[Credential-related source omitted]
```

Network accessline 636

env_log = self.root / "claude-smoke-env.txt"         self.env["PARTNER_TEST_CLAUDE_ENV"] = str(env_log)         self.env["ANTHROPIC_BASE_URL"] = "https://poisoned.example"

Network accessline 637

self.env["PARTNER_TEST_CLAUDE_ENV"] = str(env_log)         self.env["ANTHROPIC_BASE_URL"] = "https://poisoned.example"         self.env["ANTHROPIC_AUTH_TOKEN"] = "poisoned-token"

Network accessline 638

self.env["ANTHROPIC_BASE_URL"] = "https://poisoned.example"

Access to secretsline 639
```
[Credential-related source omitted]
```

`tests/test_partner_setup_ui.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 76
```
[Credential-related source omitted]
```

`tests/test_run_claude_plan.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 44
```
[Credential-related source omitted]
```
Access to secretsline 47
```
[Credential-related source omitted]
```
Access to secretsline 49
```
[Credential-related source omitted]
```
Access to secretsline 54
```
[Credential-related source omitted]
```
Access to secretsline 166
```
[Credential-related source omitted]
```
Access to secretsline 169
```
[Credential-related source omitted]
```
Access to secretsline 377
```
[Credential-related source omitted]
```

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: 115 facts

Network access in prose of documentationREADME.en.md:9Low confidence
Network access in prose of documentationREADME.en.md:10Low confidence
Network access in prose of documentationREADME.en.md:11Low confidence
Network access in prose of documentationREADME.en.md:12Low confidence
Network access in code of documentationREADME.en.md:33Low confidence
Network access in code of documentationREADME.en.md:39Low confidence
Network access in prose of documentationREADME.en.md:338Low confidence
Network access in prose of documentationREADME.en.md:340Low confidence
Network access in prose of documentationREADME.en.md:342Low confidence
Network access in prose of documentationREADME.en.md:344Low confidence
Network access in prose of documentationREADME.en.md:346Low confidence
Network access in prose of documentationREADME.md:9Low confidence
Network access in prose of documentationREADME.md:10Low confidence
Network access in prose of documentationREADME.md:11Low confidence
Network access in prose of documentationREADME.md:12Low confidence
Network access in code of documentationREADME.md:33Low confidence
Network access in code of documentationREADME.md:39Low confidence
Network access in prose of documentationREADME.md:337Low confidence
Network access in prose of documentationREADME.md:339Low confidence
Network access in prose of documentationREADME.md:341Low confidence
Network access in prose of documentationREADME.md:343Low confidence
Network access in prose of documentationREADME.md:345Low confidence
Instruction override signal in prose of documentationdocs/CHANGES.md:34Low confidence
Network access in prose of documentationdocs/TEST.md:7Low confidence
Network access in code of documentationdocs/TEST.md:22Low confidence
Network access in code of documentationdocs/TEST.md:29Low confidence
Network access in code of documentationdocs/TEST.md:30Low confidence
Network access in code of documentationdocs/TEST.md:31Low confidence
Network access in prose of documentationdocs/v1.5-dual-host-acceptance.md:7Low confidence
Network access in code of documentationdocs/v1.5-dual-host-acceptance.md:88Low confidence
Network access in code of documentationdocs/v1.5-dual-host-acceptance.md:119Low confidence
Network access in prose of documentationexamples/v2.0.1-conversation-cost-receipt.md:106Low confidence
Network access in prose of documentationexamples/v2.0.1-conversation-cost-receipt.md:107Low confidence
Network access in prose of documentationexamples/v2.0.1-conversation-cost-receipt.md:108Low confidence
Network access in prose of documentationidea-king/README.md:46Low confidence
Network access in prose of documentationidea-king/README.md:47Low confidence
Network access in prose of documentationidea-king/README.md:48Low confidence
Network access in prose of documentationidea-king/README.md:49Low confidence
Network access in prose of documentationidea-king/README.md:50Low confidence
Network access in prose of documentationidea-king/README.md:51Low confidence
Network access in prose of documentationidea-king/README.md:53Low confidence
Network access in prose of documentationidea-king/README.md:54Low confidence
Network access in prose of documentationidea-king/README.md:55Low confidence
Network access in prose of documentationidea-king/README.md:56Low confidence
Network access in prose of documentationidea-king/README.md:57Low confidence
Network access in prose of documentationidea-king/README.md:58Low confidence
Executable script in code of a file that runsinstall.sh:1High confidence
Dangerous shell operation in code of a file that runsinstall.sh:192High confidence
Dangerous shell operation in code of a file that runsinstall.sh:216High confidence
Instruction override signal in prose of documentationreferences/codex-driven.md:77Low confidence

and 65 more

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Compatible	Standard SKILL.md SKILL.md	`.claude/skills/<skill-name>/`
Codex	Compatible	Standard SKILL.md SKILL.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md 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.

LearnPrompt/partner-skill

History

SKILL.md

idea-king/SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

partner-skill

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

idea-king

Frontmatter

SKILL.md

Reference documents

The playbook

Files

Skills included

Repository facts

Before you install

README.en.md

README.md

docs/CHANGES.md

docs/TEST.md

docs/receipt-schema.json

docs/v1.5-dual-host-acceptance.md

examples/v2.0.1-conversation-cost-receipt.md

idea-king/README.md

install.sh

references/codex-driven.md

scripts/check-claude-cli.sh

scripts/check-readme-parity.py

scripts/check-skill-repo.sh

scripts/delegate-codex.sh

scripts/goal-sync.py

scripts/make-handoff.sh

scripts/make-receipt.py

scripts/partner-config.py

scripts/partner-setup-ui.py

scripts/partner-setup.py

scripts/partner_runtime.py

scripts/run-claude-plan.py

scripts/run-test-prompts.py

scripts/sandbox-matrix.sh

scripts/session-snapshot.sh

scripts/showcase-cost-ledger.py

scripts/validate-receipt.py

tests/test_delegate_role.py

tests/test_delegate_sandbox.py

tests/test_goal_sync.py

tests/test_partner_config.py

tests/test_partner_setup.py

tests/test_partner_setup_ui.py

tests/test_run_claude_plan.py

How the signals fit together

Works with

You might also use

first-fluke/oh-my-agent

dagoSte/squadra

tmcfarlane/team-avatar

jmagly/aiwg

Xiaoher-C/agentbnb

addyosmani/agent-skills

`SKILL.md`

`idea-king/SKILL.md`

`README.en.md`

`README.md`

`docs/CHANGES.md`

`docs/TEST.md`

`docs/receipt-schema.json`

`docs/v1.5-dual-host-acceptance.md`

`examples/v2.0.1-conversation-cost-receipt.md`

`idea-king/README.md`

`install.sh`

`references/codex-driven.md`

`scripts/check-claude-cli.sh`

`scripts/check-readme-parity.py`

`scripts/check-skill-repo.sh`

`scripts/delegate-codex.sh`

`scripts/goal-sync.py`

`scripts/make-handoff.sh`

`scripts/make-receipt.py`

`scripts/partner-config.py`

`scripts/partner-setup-ui.py`

`scripts/partner-setup.py`

`scripts/partner_runtime.py`

`scripts/run-claude-plan.py`

`scripts/run-test-prompts.py`

`scripts/sandbox-matrix.sh`

`scripts/session-snapshot.sh`

`scripts/showcase-cost-ledger.py`

`scripts/validate-receipt.py`

`tests/test_delegate_role.py`

`tests/test_delegate_sandbox.py`

`tests/test_goal_sync.py`

`tests/test_partner_config.py`

`tests/test_partner_setup.py`

`tests/test_partner_setup_ui.py`

`tests/test_run_claude_plan.py`