repo-archaeologist
Skill2 starsChanged 4 months agoMITView on GitHub
Use this skill when entering an unfamiliar or long-lived codebase and needing to understand not only its current structure but the historical reasons, ownership boundaries, risky seams, abandoned migrations, and unwritten conventions behind it. Base conclusions on code and version-control evidence and label inference explicitly.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- mduongvandinh/repo-archaeologisttheir own version, first seen May 14, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- mduongvandinh/repo-archaeologist★ 0same name
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 repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-proof-workSkill
- anti-slop-frontendSkill
- blast-radiusSkill
- decision-tribunalSkill
- failure-museumSkill
- grill-me-until-its-clearSkill
- launch-forensicsSkill
- scope-sniperSkill
- ux-friction-hunterSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 37
Default branch plus relevant historical branches/tags
- Distinctive: line 40
If a required input is retrievable from available tools or artifacts, retrieve it rather than asking the user.
- Distinctive: line 46
Read agent instructions, README, manifests, entrypoints, ownership, deployment, and architecture records.
- Distinctive: line 58
Use history to find frequently co-changed files, long-lived parallel implementations, reverts, compatibility layers, migrations, and …
- Distinctive: line 84
Do not narrate every directory.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Repository Archaeologist
Outcome
Explain how the repository became this way, where its real boundaries lie, and what a newcomer must not accidentally break.
This skill changes the agent's process: it requires evidence, explicit claim strength, and a checkable completion boundary. Load references/playbook.md only when deeper prompts or rubrics are needed. Use assets/output-template.md when producing the final artifact.
When to use
- The user asks for a codebase tour, architecture archaeology, onboarding map, or historical explanation.
- A legacy repository has unclear boundaries, parallel systems, or suspicious conventions.
- A change requires understanding why a fragile area exists before editing it.
Do not use when
- The user needs only a file or symbol lookup.
- The repository is new and has little meaningful history.
Required inputs
- Repository and intended change or learning goal
- Default branch plus relevant historical branches/tags
- README, architecture records, ownership files, issue links, and git history
If a required input is retrievable from available tools or artifacts, retrieve it rather than asking the user. Ask only when a missing answer represents authority, preference, or risk that tools cannot resolve.
Workflow
1. Orient from declared intent
Read agent instructions, README, manifests, entrypoints, ownership, deployment, and architecture records. Record what the repository claims to be.
Complete when: declared architecture and instructions are summarized
2. Map runtime reality
Trace entrypoints, major modules, data flows, integration boundaries, generated code, build/deploy paths, and tests. Distinguish directory structure from actual runtime coupling.
Complete when: actual execution paths and boundaries are evidenced
3. Excavate hotspots
Use history to find frequently co-changed files, long-lived parallel implementations, reverts, compatibility layers, migrations, and comments naming constraints.
Complete when: historical hotspots relevant to the goal are identified
4. Reconstruct decision strata
Build a chronology of major architectural eras. For each inferred decision, cite evidence and assign confirmed, strongly supported, or speculative confidence.
Complete when: rationale claims carry confidence and citations
5. Identify social architecture
Map CODEOWNERS, review patterns when available, subsystem maintainers, and operational ownership. Do not infer individual responsibility from blame alone.
Complete when: ownership claims avoid blame-based inference
6. Create the field guide
Explain the system, historical layers, conventions, dangerous seams, safe starting points, and questions that require maintainers. Tailor depth to the intended change.
Complete when: a newcomer knows where to start and what remains uncertain
Operating rules
- Current code is evidence of behavior, not necessarily of original intent.
- Git blame identifies a commit, not a person to blame.
- Do not narrate every directory; prioritize decision-relevant structure.
- Mark generated, vendored, and deprecated areas clearly.
- Separate directly documented facts from historical inference.
Output contract
The final result must contain:
- One-page system orientation
- Runtime and dependency map
- Architecture chronology with confidence
- Hotspots and dangerous seams
- Unwritten conventions with evidence
- Change-specific reading path and maintainer questions
Distinguish observed, inferred, assumed, and unverified claims. Link to files, commits, screenshots, commands, logs, or supplied sources when those artifacts support a consequential conclusion. Keep the executive result concise; move detail behind appendices when necessary.
Common pitfalls
- Directory tourism without tracing runtime behavior.
- Inventing rationale from code shape alone.
- Treating newest architecture as universally preferred when migration is incomplete.
- Using churn as a synonym for poor quality.
Verification checklist
- The requested outcome—not merely the procedure—has been satisfied.
- Every consequential claim is supported, qualified, or explicitly unverified.
- The workflow's completion criteria are met in order.
- Safety boundaries and forbidden side effects were respected.
- The output follows
assets/output-template.mdor contains equivalent information. - Remaining unknowns have an owner, next action, or stated consequence.
Resources
references/playbook.md— deeper domain prompts and evaluation guidance.assets/output-template.md— reusable final-output structure.evals/evals.json— output-quality cases.evals/trigger-evals.json— positive and negative description-trigger cases.
Does 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.

