agentleFS
ssarunicssarunic/job-radar/AGENTS.md

job-radar

AGENTS.md0 starsChanged 5 months agoMITView on GitHub

Guidance for coding agents (Codex, etc.) working in this repository. This repo is implemented, not spec-only. The authoritative docs, in order: 1. specs/constitution.md — non-negotiable principles (local-first; Markdown canonical / JSONL derived; crawler ethics; never overwrite user-owned content). 2. specs/build-spec.md — the build/architecture spec: storage layout, scraping ladder, ATS adapters, and fetching policy live here. 3. CLAUDE.md — working guidance + the domain rules that are easy to get wrong (seniority ranking, title/employment/location filters, salary, lifecycle). 4. README.md — the…

  • 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 33,315 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 repository2 other files it gives its agents.

The file

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

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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
  1. Distinctive:

    If these ever disagree, the constitution wins, then build-spec, then CLAUDE.md.

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 42,283 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

Guidance for coding agents (Codex, etc.) working in this repository.

Source of truth (read these first)

This repo is implemented, not spec-only. The authoritative docs, in order:

  1. specs/constitution.md — non-negotiable principles (local-first; Markdown canonical / JSONL derived; crawler ethics; never overwrite user-owned content).
  2. specs/build-spec.md — the build/architecture spec: storage layout, scraping ladder, ATS adapters, and fetching policy live here.
  3. CLAUDE.md — working guidance + the domain rules that are easy to get wrong (seniority ranking, title/employment/location filters, salary, lifecycle).
  4. README.md — the original product/domain spec. Historical for storage & output (it predates the Markdown store and describes XLSX); defer to specs/build-spec.md for anything about how data is stored or fetched.

If these ever disagree, the constitution wins, then build-spec, then CLAUDE.md; README is last and only for product/domain intent.

Architecture in one paragraph

Python CLI (main.py, Click) + a uv/FastAPI + React web app (webapp/). Two modes: seek (find/rank senior PM roles) and enrich (company facts). Canonical store is Markdown with frontmatter (jobs/<company>/<role>--<id>.md); data/jobs.jsonl is a derived index. Fetching uses a scraping ladder (ATS JSON API → optional Playwright → static HTML) with 9 ATS adapters. Claude is used only for fuzzy parsing and is off by default, always with a heuristic fallback. Store paths resolve through services/store.py (honours JSA_ROOT).

Deployed via CI/CD (push a vX.Y.Z tag → GitHub Actions → arm64 image → GHCR → push-deploy over Tailscale SSH) to a Raspberry Pi; the scraper runs daily at 08:00 and posts new roles to Slack. See specs/deploy.md (and [[deploy-pipeline]] memory).

Lint/test (CI-gated, run before pushing): ruff check . (config in ruff.toml; broad except is an intentional pattern so BLE is off), python -m pytest tests/ webapp/backend/tests/ -q, and in webapp/frontend/: npm run lint (ESLint) + npm run build.

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.