agentleFS
mikkiolamikkiola/radar/CLAUDE.md

radar

CLAUDE.md2 starsChanged 27 days agoMITView on GitHub

Radar's code branch contains collection, assessment, pattern and publication logic. Its separate vault branch holds pipeline data. Start with the section "How every repository works" of the universal rules: the reading order, the file that wins on a conflict, how a rule changes, and what each document is for. If docs/tooltempest/universal-rules.md is missing: stop and run, from the repository root: The command reads repository and commit from .tooltempest.lock, uses a new temporary clean checkout that it removes on exit, and…

  • Deletes or force-pushes
  • In this repositoryOne other file it gives its agents.

The file

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

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start with the section "How every repository works" of the universal rules: the reading order, the file that wins on a conflict, how a rule …

    line 8
  2. Very specific:

    If docs/tooltempest/universal-rules.md is missing: stop and run, from the repository root:

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md

Radar project entry point

Radar's code branch contains collection, assessment, pattern and publication logic. Its separate vault branch holds pipeline data.

Sources of truth

Start with the section "How every repository works" of the universal rules: the reading order, the file that wins on a conflict, how a rule changes, and what each document is for. If docs/tooltempest/universal-rules.md is missing: stop and run, from the repository root:

( set -eu; D=$(mktemp -d "${TMPDIR:-/tmp}/tooltempest.XXXXXX"); trap 'rm -rf "$D"' EXIT; R=$(python3 -c 'import json; print(json.load(open(".tooltempest.lock"))["repository"])'); C=$(python3 -c 'import json; print(json.load(open(".tooltempest.lock"))["commit"])'); git clone -q --no-checkout "$R" "$D"; git -C "$D" checkout -q --detach "$C"; python3 "$D/scripts/tooling.py" materialize --root . --source "$D" --apply )

The command reads repository and commit from .tooltempest.lock, uses a new temporary clean checkout that it removes on exit, and does not touch any other ToolTempest clone. Project rules are in CONSTITUTION; SPEC holds the bounded implementation requirements. This file routes to these sources. The working rules for code and tests are in Constitution sections 5 and 6; for task discipline and neighboring projects, in section 15.

Code and tests

  • src contains pipeline modules, including model/network entry points.
  • tests contains the existing pytest cases; scope and source-path configuration are in pyproject.toml.
  • README describes the repository and existing execution surfaces.

Example test commands:

python3 -m pytest tests/test_vault_write.py -q
python3 -m pytest tests/test_check_frontmatter.py -q

Pipeline rules: .claude/rules/pipeline.md.

Existing workflows

The session-end skill handles BACKLOG closure, not Article Pipeline's structural sync procedure.

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.