agentleFS
Sign inStart free
J3d1-fmJ3d1-fm/Personal-Task-Assistant/AGENTS.md

Personal-Task-Assistant

AGENTS.md0 starsChanged 3 months agoMITView on GitHub

This file is the entry point for any coding agent (Codex, Claude Code, or other) working in this repository. Read it before changing anything. Personal Task Assistant is not a classic task tracker: it is the coordination layer between a human and autonomous AI agents. Humans decide, agents execute, and both share one operational queue. The JSON API is the agent contract, the MCP server (adapters/task_assistant_mcp.py) is the native way for agents to operate the board, and the web UI…

  • Reads credentials
  • Installs packages
  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository6 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Every shipped change bumps app_version in app/config.py and gets a detailed CHANGELOG.txt entry in the established style.

    line 37
  2. Very specific:

    Never commit credentials, tokens, .env values, or databases.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AGENTS.md

AGENTS.md — Operating Contract

This file is the entry point for any coding agent (Codex, Claude Code, or other) working in this repository. Read it before changing anything.

What this project is

Personal Task Assistant is not a classic task tracker: it is the coordination layer between a human and autonomous AI agents. Humans decide, agents execute, and both share one operational queue. The JSON API is the agent contract, the MCP server (adapters/task_assistant_mcp.py) is the native way for agents to operate the board, and the web UI is the human's operating surface.

Skills — read the matching one BEFORE working

Playbooks distilled from real development sessions live in .claude/skills/. Claude Code discovers them automatically; every other agent must open the matching SKILL.md manually. Match by task:

You are about to...Read first
Work tasks from the board as the agent (claim/finish/ingest).claude/skills/task-board-worker/SKILL.md
The daily scheduled run / digest / automation/.claude/skills/daily-task-ritual/SKILL.md
Commit/ship ANY change (version, changelog, CI).claude/skills/ship-release/SKILL.md
Touch the DB schema, models, or migrations.claude/skills/db-schema-change/SKILL.md
Touch the MCP tools or their descriptions.claude/skills/mcp-tool-change/SKILL.md

Ground rules

  • Python 3.12+, FastAPI + SQLAlchemy; SQLite in Local Mode, Firestore on Cloud Run. Setup: python3 -m venv .venv && .venv/bin/pip install -r requirements.txt -r requirements-dev.txt.
  • Lint and tests must be green before any commit: .venv/bin/ruff check . and .venv/bin/pytest -q (CI runs exactly these).
  • Schema changes go through Alembic revisions only — never Base.metadata.create_all (see the db-schema-change skill for why).
  • Every shipped change bumps app_version in app/config.py and gets a detailed CHANGELOG.txt entry in the established style.
  • Never commit credentials, tokens, .env values, or databases. The eval board (evals/eval_board.db) is disposable; never point evals at a real working database.
  • Local dev auth is loopback-only by design; do not weaken it.

Map

  • app/ — FastAPI app: main.py (routes), store.py (SQLite + Firestore stores), models.py/schemas.py, migrate.py (Alembic runner with legacy-DB stamping), auth.py, history.py (Sheets export).
  • migrations/ — Alembic revisions (numbered 000N_*.py).
  • adapters/ — connectors: Telegram polling adapter, MCP server.
  • tests/ — pytest suite; MCP tools are tested against the in-process app.
  • evals/ — agent evaluation process for the MCP server (seeded board, questions, deterministic verifier, LLM harness). See evals/README.md.
  • automation/ — the once-a-day ritual: health check + digest (deterministic) and an opt-in agent work loop; scheduled via launchd/systemd/cron natively or automation/scheduler.py in Docker. See automation/README.md.
  • docker-compose.yml + docs/SELF_HOSTING.md — the standalone deployment (tracker + daily ritual as services); releases are tagged vX.Y.Z and published by .github/workflows/release.yml from CHANGELOG.txt.
  • docs/ — API, MCP, install, PM guide; CHANGELOG.txt is the release log.

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.

Check your setup, free