code-investigate
Skill192 starsChanged 36 days agoMITView on GitHub
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.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- sd0xdev/sd0x-harnessword for word, first seen Oct 6, 2026
Other versions1 project uses a version of this.
Word for word · 1
- sd0xdev/sd0x-harness★ 192100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository102 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adrSkill
- agentctl-setupSkill
- architectureSkill
- askSkill
- best-practicesSkill
- bug-fixSkill
- bump-versionSkill
- check-coverageSkill
- claude-healthSkill
- code-exploreSkill
- codex-architectSkill
- codex-brainstormSkill
- codex-cli-reviewSkill
- codex-code-reviewSkill
- codex-explainSkill
- codex-implementSkill
- codex-review-branchSkill
- codex-review-docSkill
- codex-review-fastSkill
- codex-reviewSkill
- codex-securitySkill
- codex-setupSkill
- codex-test-genSkill
- codex-test-reviewSkill
- contract-decodeSkill
- create-prSkill
- create-requestSkill
- de-ai-flavorSkill
- debugSkill
- deep-analyzeSkill
- deep-exploreSkill
- deep-researchSkill
- dep-auditSkill
- deploy-flowSkill
- dev-security-auditSkill
- doc-refactorSkill
- doc-reviewSkill
- epic-mergeSkill
- feasibility-studySkill
- feature-devSkill
- feature-verifySkill
- fp-briefSkill
- generate-runnerSkill
- gh-stackSkill
- git-investigateSkill
- git-profileSkill
- install-hooksSkill
- install-rulesSkill
- install-scriptsSkill
- issue-analyzeSkill
- jiraSkill
- load-pr-reviewSkill
- merge-prepSkill
- necessity-auditSkill
- next-stepSkill
- obsidian-cliSkill
- op-sessionSkill
- orchestrateSkill
- plan-reviewSkill
- The first 60 shown.
The file
Files
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.
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 causesDoes it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

