PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Dual-perspective code investigation. An agent skill from sd0xdev/sd0x-harness.
Install Code Investigate
$ npx skills add sd0xdev/sd0x-harness --skill code-investigate -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install sd0xdev/sd0x-harness code-investigate --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/sd0xdev/sd0x-harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/code-investigate .claude/skills/code-investigate && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "code-investigate" agent skill from https://github.com/sd0xdev/sd0x-harness/tree/main/skills/code-investigate into .claude/skills/code-investigate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-investigate", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/sd0xdev/sd0x-harness/tree/main/skills/code-investigateType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add sd0xdev/sd0x-harness --skill code-investigate -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install sd0xdev/sd0x-harness code-investigate --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sd0xdev/sd0x-harness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/code-investigate .agents/skills/code-investigate && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "code-investigate" agent skill from https://github.com/sd0xdev/sd0x-harness/tree/main/skills/code-investigate into .agents/skills/code-investigate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-investigate", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sd0xdev/sd0x-harness --skill code-investigate -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install sd0xdev/sd0x-harness code-investigate --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sd0xdev/sd0x-harness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/code-investigate .cursor/skills/code-investigate && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "code-investigate" agent skill from https://github.com/sd0xdev/sd0x-harness/tree/main/skills/code-investigate into .cursor/skills/code-investigate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-investigate", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/sd0xdev/sd0x-harness.git --path skills/code-investigate--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add sd0xdev/sd0x-harness --skill code-investigate -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install sd0xdev/sd0x-harness code-investigate --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sd0xdev/sd0x-harness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/code-investigate .gemini/skills/code-investigate && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "code-investigate" agent skill from https://github.com/sd0xdev/sd0x-harness/tree/main/skills/code-investigate into .gemini/skills/code-investigate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-investigate", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install sd0xdev/sd0x-harness code-investigateInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add sd0xdev/sd0x-harness --skill code-investigate -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/sd0xdev/sd0x-harness.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/code-investigate .github/skills/code-investigate && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "code-investigate" agent skill from https://github.com/sd0xdev/sd0x-harness/tree/main/skills/code-investigate into .github/skills/code-investigate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-investigate", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sd0xdev/sd0x-harness --skill code-investigate -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install sd0xdev/sd0x-harness code-investigate --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sd0xdev/sd0x-harness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/code-investigate .opencode/skills/code-investigate && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "code-investigate" agent skill from https://github.com/sd0xdev/sd0x-harness/tree/main/skills/code-investigate into .opencode/skills/code-investigate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-investigate", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
code-investigate- GitHub stars
- 192
- Token cost
- ~1.5k tokens
- SKILL.md length
- 339 words
- Files
- 3 (incl. references)
- Skills in repo
- 91
- Repo updated
- First seen
- Licence
- MIT
At a glance
Dual-perspective code investigation. An agent skill from sd0xdev/sd0x-harness.
- Works in 4 steps: What files are related? → How does the core logic work? → What is the data flow? → …
- : deep code analysis needing both Claude and Codex perspectives
- SKILL.md covers Trigger, When NOT to Use, Core Principle and Workflow, plus 8 more sections
- Calls codex, git and claude
What it does
Code Investigate is an agent skill from sd0xdev/sd0x-harness. Dual-perspective code investigation. Use when: deep code analysis needing both Claude and Codex perspectives. Not for: quick exploration (use code-explore), code review (use codex-code-review). Output: integrated findings from dual analysis.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/output-template.md` and `references/prompts.md`).
It sits in Development, covering Code review. The repository describes itself as: The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and… The licence is MIT.
When your agent uses it
- : deep code analysis needing both Claude and Codex perspectives
- Tasks that involve Code review
Example prompts
- “/code-investigate”
Requirements
- Pre-approved tools (allowed-tools): Read, Grep, Glob, Bash(git:*), Bash(node:*), Write
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- What files are related?
- How does the core logic work?
- What is the data flow?
- What are the key dependencies?
What it can do on your machine
Read from SKILL.md and the folder at commit c9a2036. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ReadGrepGlobBash(git:*)Bash(node:*)Write
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
codexgitclaude
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Code Investigate loads about 1.5k tokens when it runs, and up to ~3.4k if it reads all its reference files. Until then it costs about 65 tokens; SKILL.md has 339 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from sd0xdev/sd0x-harness at commit c9a2036, republished under its MIT licence (© sd0xdev). 339 words, ~1,509 tokens.
Download SKILL.mdSave it as
.claude/skills/code-investigate/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- code-investigate
- description
- Dual-perspective code investigation. Use when: deep code analysis needing both Claude and Codex perspectives. Not for: quick exploration (use code-explore), code review (use codex-code-review). Output: integrated findings from dual analysis.
- allowed-tools
- Read, Grep, Glob, Bash(git:*), Bash(node:*), Write
- context
- fork
Code Investigate Skill
Trigger
- Keywords: investigate code, how feature works, trace implementation, dual confirmation, deep dive, how code works, what this code does, code research
When NOT to Use
- Just need quick lookup (use Grep/Glob directly)
- Code review (use codex-review)
- System verification (use feature-verify)
- Git history tracking (use git-investigate)
Core Principle
Codex must explore independently. Feeding Claude's conclusions to Codex is prohibited.┌─────────────────┐ ┌─────────────────┐
│ Claude Explores │ │ Codex Explores │
│ Independently │ │ Independently │
│ (Phase 1-2) │ │ (Phase 3) │
└────────┬────────┘ └────────┬────────┘
│ │
▼ ▼
┌───────────┐ ┌───────────┐
│ Claude │ │ Codex │
│ Conclusion│ │ Conclusion│
└─────┬─────┘ └─────┬─────┘
│ │
└───────────┬───────────┘
▼
┌─────────────┐
│ Consolidated│
│ Report │
│ (Phase 4) │
└─────────────┘Workflow
| Phase | Name | Action | Output |
|---|---|---|---|
| 1 | Claude Explore | Grep/Glob/Read to search code | Related files list |
| 2 | Claude Conclude | Analyze logic, form understanding | Initial conclusion (internal) |
| 3 | Codex Explore | Invoke Codex exec to explore independently | Codex analysis report |
| 4 | Integrate | Compare both perspectives, mark differences | Consolidated report |
Codex Invocation Rules
Dispatch Phase 3 per @skills/codex-code-review/references/codex-transport.md § Start with the template in references/prompts.md. The transport
pins the sandbox and the approval policy, and it derives the working directory from
git rev-parse --show-toplevel — none of the three is chosen here, and this skill no longer
restates them.
Bind every placeholder before writing prompt.md. The template is body-only, so nothing
evaluates an expression inside it: ${USER_QUESTION} and ${PROJECT_PATH} must carry real values
by the time the file is written.
Correct Approach
Code Investigation Task
Question
${USER_QUESTION}
Project Info
- Path: ${PROJECT_PATH}
- Tech Stack: ${TECH_STACK}
<!-- one bound value, read from the repository's own manifest and layout. `{FRAMEWORK}`/`{DATABASE}` were never in this file's binding contract and rendered literally, and the hard-coded `TypeScript` was false for any repository that is not one — this project is JavaScript. Omit the line entirely rather than guess. -->
Please independently explore the codebase and answer:
- What files are related?
- How does the core logic work?
- What is the data flow?
- What are the key dependencies?
Please grep/read and explore on your own, then provide your analysis.
Show full SKILL.md (108 more words)Show less
Prohibited Approaches
| Pattern | Problem | Example |
|---|---|---|
| Feeding conclusion | Claude's findings leak to Codex | Claude found these files: ${findings} |
| Leading question | Presupposes answer | I think the problem is in cache, verify |
| Scope restriction | Prevents independent exploration | Only look at src/service/ |
Output
## Investigation Report
- **Claude findings**: <independent analysis>
- **Codex findings**: <independent analysis>
- **Integrated conclusion**: <merged findings>
- **Confidence**: High / Medium / LowVerification Checklist
| Check | Standard |
|---|---|
| Claude independent conclusion | Phase 2 forms conclusion, not output to user |
| Codex prompt is clean | Contains only question + project path, no Claude findings |
| Report perspectives separated | Claude / Codex conclusions presented separately |
| Integration is complete | Marks agreement, differences, possible gaps |
References
| File | Purpose | When to Read |
|---|---|---|
references/prompts.md | Codex prompt templates | Before Phase 3 |
references/output-template.md | Report format | During Phase 4 |
Examples
Feature Investigation
Input: Investigate how order processing works
Phase 1: Grep "processOrder" -> Read src/service/order/*.ts
Phase 2: Form understanding: Controller -> Service -> Repository write
Phase 3: Codex explores independently (only given question + path)
Phase 4: Consolidated report -> mark both perspectivesMechanism Understanding
Input: How does the API caching mechanism work?
Phase 1: Grep "cache" + "portfolio" -> Read related files
Phase 2: Understand Redis TTL + fallback mechanism
Phase 3: Codex investigates independently
Phase 4: Compare differences -> output consolidated reportProblem Diagnosis
Input: Why is token price sometimes null?
Phase 1: Search price-related logic + error handling
Phase 2: Identify possible fallback paths
Phase 3: Codex diagnoses independently
Phase 4: Synthesize both findings -> list possible causes© sd0xdev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (references) in skills/code-investigate of sd0xdev/sd0x-harness.
- SKILL.md
- references/output-template.md
- references/prompts.md
Open the folder on GitHubat commit c9a2036
Compare with similar skills
Code Investigate next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Code Investigate this skillsd0xdev/sd0x-harness | 192 | — | ~1.5k | Automated safety check: Pass | MIT | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Backend Code Reviewlangflow-ai/langflow | 156k | — | ~3.5k | Automated safety check: Notes | MIT | |
| Understand Diff AnalysisEgonex-AI/Understand-Anything | 85k | 1 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Mole Bug Patternstw93/Mole | 69k | — | ~2k | Automated safety check: Pass | GPL-3.0 |
Similar skills
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Backend Code Review
langflow-ai/langflow
Review backend code for quality, security, maintainability, and best practices based on established checklist rules.
Understand Diff Analysis
Egonex-AI/Understand-Anything
Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.
Mole Bug Patterns
tw93/Mole
A catalog of recurring bug shapes in the Mole Mac cleaner, used to review safety-sensitive diffs for deletion safety, unbounded commands, shell traps and weak tests.
Backend Code Review
langgenius/dify
Reviews backend code under api/ for concrete, reproducible defects, routes to rule packs for architecture, schema, repositories and SQLAlchemy, and ranks findings from P0 to P3.
More from sd0xdev/sd0x-harness
All 91 skills in this repoAdr
sd0xdev/sd0x-harness
Write an Architecture Decision Record (ADR) for a feature — Context / Decision / Status / Consequences / Alternatives, filed as docs/features/<feature/adr-<NNN-<title.md with a 3-digit zero-padded…
Load PR Review
sd0xdev/sd0x-harness
Load GitHub PR review comments into AI session — analyze, triage, plan.
Next Step
sd0xdev/sd0x-harness
Change-aware next step advisor. An agent skill from sd0xdev/sd0x-harness.
Obsidian CLI
sd0xdev/sd0x-harness
Obsidian vault integration via official CLI. An agent skill from sd0xdev/sd0x-harness.
Orchestrate
sd0xdev/sd0x-harness
Agent-driven workflow orchestration (v1 report-only). An agent skill from sd0xdev/sd0x-harness.
PR Comment
sd0xdev/sd0x-harness
Post friendly review comments to a GitHub PR — prepare locally, preview, then submit as atomic review.
Related
Categories
Questions about Code Investigate
What does Code Investigate do?
Dual-perspective code investigation. An agent skill from sd0xdev/sd0x-harness. Code Investigate is an agent skill from sd0xdev/sd0x-harness. Dual-perspective code investigation.
When should I use Code Investigate?
Code Investigate fits situations like: : deep code analysis needing both Claude and Codex perspectives; tasks that involve Code review.
How do I install Code Investigate in Claude Code?
Run `npx skills add sd0xdev/sd0x-harness --skill code-investigate -a claude-code`. Or copy the skill folder (skills/code-investigate in sd0xdev/sd0x-harness) into .claude/skills/code-investigate in your project. Claude Code loads it when a task matches its description.
How do I install Code Investigate in Codex?
Run `npx skills add sd0xdev/sd0x-harness --skill code-investigate -a codex`. Or copy the skill folder (skills/code-investigate in sd0xdev/sd0x-harness) into .agents/skills/code-investigate in your project. Codex loads it when a task matches its description.
Can I use Code Investigate in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sd0xdev/sd0x-harness --skill code-investigate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-investigate, .gemini/skills/code-investigate, .github/skills/code-investigate and .opencode/skills/code-investigate in your project.
What does Code Investigate need to run?
Going by SKILL.md and its folder, Code Investigate needs the command-line tools its instructions call (codex, git and claude). Its frontmatter pre-approves these tools: Read, Grep, Glob, Bash(git:*), Bash(node:*), Write.
Does Code Investigate access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Code Investigate safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Code Investigate use?
Code Investigate is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Code Investigate use?
About 1.5k tokens (SKILL.md is roughly 6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.9k tokens, read only when the agent opens those files.
What are the alternatives to Code Investigate?
Skills that share tags, products or a category with Code Investigate: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Backend Code Review (langflow-ai/langflow, 156k stars) and Understand Diff Analysis (Egonex-AI/Understand-Anything, 85k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Code Investigate?
sd0xdev (a GitHub user) maintains it in sd0xdev/sd0x-harness, which has 192 GitHub stars. The repository holds 91 skills in this directory. The repository was last updated on October 6, 2026.
Source: sd0xdev/sd0x-harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.