agentleFS
gonun13gonun13/agent-skills/skills/repo-recon/SKILL.md

repo-recon

Skill0 starsChanged 2 months agoMITView on GitHub

Surveys an unfamiliar codebase — what it is, how it builds, and where to start. Use when orienting in a repo you have not worked in before.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check first: the README, the package or build manifest (package.json, pyproject.toml, go.mod, Cargo.toml, pom.xml, ...), any CONTRIBUTING …

    line 15
  2. Distinctive:

    Check git log --oneline -20 and the branch layout for where work is currently concentrated.

    line 33
  3. Distinctive:

    Read only, apart from the briefing file.

    line 38
  4. Distinctive:

    Every section below is filled from evidence in the repo, with unresolved items listed under Unknowns rather than guessed at.

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Repo recon

Goal

An orientation briefing accurate enough that a competent engineer who has never seen this repository can start work from it.

Context

Check first: the README, the package or build manifest (package.json, pyproject.toml, go.mod, Cargo.toml, pom.xml, ...), any CONTRIBUTING file, and the docs/ entry point.

Steps

  1. Identify what the project is and who it is for.
  2. Determine the languages, frameworks, and how it is built, run, and tested. Quote the actual commands from the manifest or CI config rather than assuming the conventional ones.
  3. Map the top-level layout, one line per significant directory. Skip vendored code, lockfiles, build output, and dependency directories.
  4. Find the entry points: main, server bootstrap, CLI definition, exported package surface, or route table.
  5. Locate the tests: where they live, which runner, and roughly how much of the codebase they appear to cover.
  6. Note the operational surface: configuration files, environment variables, secrets handling, CI workflows, deploy or container definitions.
  7. Check git log --oneline -20 and the branch layout for where work is currently concentrated.

Constraints

  • Read only, apart from the briefing file. Do not change other files, propose refactors, or argue for a redesign.
  • Quote what the repo says; when something cannot be determined, say so and name the file that would answer it.

Done when

Every section below is filled from evidence in the repo, with unresolved items listed under Unknowns rather than guessed at.

Output

Save the briefing to RECON.md at the repo root, replacing any earlier one, with one section each, in this order:

  • What this is
  • Stack
  • Build / run / test
  • Layout
  • Entry points
  • Tests
  • Configuration and secrets
  • Where the work is
  • Unknowns

Reference files as path:line.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.