agentleFS
jmolzjmolz/m0lz.01/.agents/skills/source-command-prime/SKILL.md

source-command-prime

Skill0 starsChanged 6 months agoMITView on GitHub

Orient on the codebase before starting any work

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Use this skill when the user asks to run the migrated source command prime.

    line 8
  2. Distinctive:

    Read these files (skip any that don't exist):

    line 23
  3. Distinctive:

    Read key config files:

    line 36

≈ “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

source-command-prime

Use this skill when the user asks to run the migrated source command prime.

Command Template

Prime: Load Project Context

Objective

Build a mental model of this codebase so you can make informed decisions about what to build next.

Process

1. Read Core Documentation

Read these files (skip any that don't exist):

  • AGENTS.md — global rules and conventions
  • PRD.md or .codex/PRD.md — product requirements
  • README.md — project overview
  • Any architecture docs referenced in AGENTS.md

2. Explore Project Structure

tree -L 3 -I 'node_modules|__pycache__|.git|dist|build|.next|venv*|.venv' 2>/dev/null || find . -maxdepth 3 -not -path '*/node_modules/*' -not -path '*/.git/*' -not -path '*/dist/*' -not -name '*.pyc' | head -80

Read key config files:

  • package.json, pyproject.toml, Cargo.toml (whichever exists)
  • tsconfig.json, vite.config.*, next.config.* (if present)
  • Database config/schema files

3. Check Git History (Long-Term Memory)

git log -15 --oneline 2>/dev/null
git status 2>/dev/null
git branch --show-current 2>/dev/null
git worktree list 2>/dev/null

4. Identify Key Entry Points

Based on structure, read the first 50-80 lines of:

  • Main entry points (index.ts, main.py, app.py, etc.)
  • Core route/handler files
  • Key model/schema definitions

5. Check for Pending Work

Look for:

  • HANDOFF.md — previous session left notes
  • .codex/plans/*.md — pending implementation plans
  • Open TODOs in recent commits

If HANDOFF.md exists, cross-reference its open items against git log to verify they're still relevant. The vet-handoff hook may have already flagged stale items at session start — check for "HANDOFF.md Vet" warnings in the session transcript and act on them. Remove or mark completed any items that git history shows have been addressed. If all items are resolved, note that the handoff is fully resolved and can be deleted.

Output Report

Summarize in under 300 words with bullet points:

Project Overview

  • What this project does
  • Tech stack and key libraries
  • Current state (early, mid-build, mature)

Architecture

  • How code is organized
  • Key patterns and conventions
  • Important files and directories

Current State

  • Active branch and recent work
  • Any uncommitted changes
  • Active worktrees and their feature branches (if any)
  • Pending plans or handoffs
  • Handoff status: which items are resolved vs. still open, whether HANDOFF.md should be cleaned up or deleted

Recommended Next Action

  • What phase from the PRD comes next (if greenfield)
  • What the most impactful next task is
  • Any blockers or setup needed first

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.