agentleFS
aniketshukla1aniketshukla1/sdlc-kit/.cursor/skills/codebase-explore/SKILL.md

codebase-explore

Skill1 starsChanged 10 days agoMITView on GitHub

Phase 2. Finds the files, patterns and test setup relevant to a ticket without editing anything. Use after ticket intake and before planning.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 are 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.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read only. Do NOT edit code in this phase.

    line 7
  2. Very specific:

    Read .agent/work/<KEY>/REQUIREMENTS.md and PROGRESS.md.

    line 10
  3. Very specific:

    Check the test setup: ls backend/tests frontend/playwright.config.* frontend/cypress.config.* 2>/dev/null For the screen this ticket …

    line 18
  4. Very specific:

    Check if Elasticsearch is used: ls backend/app/search 2>/dev/null.

    line 21
  5. Very specific:

    Write "Codebase notes" in PROGRESS.md (template below) and set Phase: 2-explore (done).

    line 25
  6. Distinctive:

    Read at most ~15 files. Use line ranges for long files.

    line 28
  7. Distinctive:

    Write down facts you saw. If something is unclear, write "UNKNOWN: ..." and ask in the plan.

    line 29

≈ “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

Codebase explore (phase 2)

Read only. Do NOT edit code in this phase.

Steps

  1. Read .agent/work/<KEY>/REQUIREMENTS.md and PROGRESS.md.
  2. Map the layout (names only, no file contents yet): ls backend/app backend/app/* frontend/src frontend/src/features 2>/dev/null
  3. For each key noun/verb in the requirements (e.g. "invoice", "cancel"): rg -n -i "<term>" backend/app frontend/src --max-count 3 (no rg? use git grep -n -i "<term>")
  4. Pick the PATTERN SOURCE: the existing feature most similar to this ticket (e.g. another list + detail + form). Read its route, schema, service, repository, model, api hook, main component and one test of each kind. These are the files you will copy patterns from.
  5. Check the test setup: ls backend/tests frontend/playwright.config.* frontend/cypress.config.* 2>/dev/null For the screen this ticket touches, find its existing e2e spec: rg -l -i "<screen name>" frontend/e2e frontend/cypress
  6. Check if Elasticsearch is used: ls backend/app/search 2>/dev/null.
  7. Find existing error classes and auth dependencies: rg -n "class \w+Error" backend/app/core and rg -n "def get_current_user" backend/app
  8. Line count every file you expect to edit: wc -l <files>.
  9. Write "Codebase notes" in PROGRESS.md (template below) and set Phase: 2-explore (done).

Limits

  • Read at most ~15 files. Use line ranges for long files.
  • Write down facts you saw. If something is unclear, write "UNKNOWN: ..." and ask in the plan.

Codebase notes template

## Codebase notes
Pattern source: <feature name>
| File | Purpose | Lines |
|------|---------|-------|
| backend/app/api/v1/routes/orders.py | orders endpoints (pattern) | 142 |

- Error classes: NotFoundError, ConflictError (app/core/errors.py)
- Auth dependency: get_current_user (app/api/deps.py)
- Tests: pytest unit+integration; Vitest; E2E for this screen: Playwright (frontend/e2e/orders.spec.ts)
- Elasticsearch: yes/no
- Files near 200 lines (need split): ...
- UNKNOWN: ...

Done when

  • Pattern source chosen and its files listed
  • Test frameworks and the E2E location for this screen recorded
  • Files near the 200-line limit listed

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.