agentleFS
Sign inStart free
thrillmadethrillmade/clud-bug/AGENTS.md

clud-bug

AGENTS.md1 starsChanged 5 months agoMITView on GitHub

This is the canonical instruction file for AI coding agents working in this repository. Tools that understand AGENTS.md (Cursor, Codex, Windsurf, Claude Code, Cline, Continue, Aider, ...) read this file directly. Per-tool files like CLAUDE.md or .cursorrules are stubs that point here so the guidance lives in one place. logmind log replaces git add + git commit + git push for any change that carries a decision — do not run those git commands directly. This project uses logmind. What…

  • Commits and pushes
  • 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 31,774 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

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:

    Read that skill before pushing fixes addressing prior review threads.

    line 38

≈ “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

This is the canonical instruction file for AI coding agents working in this repository. Tools that understand AGENTS.md (Cursor, Codex, Windsurf, Claude Code, Cline, Continue, Aider, ...) read this file directly. Per-tool files like CLAUDE.md or .cursorrules are stubs that point here so the guidance lives in one place.

<!-- logmind-start --><!-- logmind-block-version: v7-pointer -->

Decision logging — logmind log is the commit primitive

logmind log replaces git add + git commit + git push for any change that carries a decision — do not run those git commands directly.

logmind log "summary" -r "why" -a "alternative" -i "implication"

This project uses logmind. What counts as a decision, branch routing, --stage scoped for unrelated WIP, logmind doctor, and the required-reading list (docs/timeline.md, docs/decisions.md, docs/file-structure.md, docs/decisions-branches/<branch>.md) all live in the logmind agent skill at https://github.com/thrillmade/agent-skills/tree/main/skills/logmind.

<!-- logmind-end -->

Project Overview

<!-- Replace with a short description of what this project does. -->

Development Commands

<!-- Common commands a contributor needs (build, test, lint, run). --><!-- clud-bug-start --><!-- clud-bug-block-version: v2 -->

clud-bug — Claude PR review

This repo uses clud-bug for automatic PR reviews. Full collaboration rules — fix-push flow, skill structure, comment format, strict-mode mechanics, workflow-edit constraint — live in the bundled clud-bug-collaboration skill. Read that skill before pushing fixes addressing prior review threads.

Strict mode is on in this repo (workflow check fails on critical findings). Toggle via .claude/skills/.clud-bug.json (read from PR base ref, so PRs can't disable strict-mode on themselves).

Local max mode (this session, on a PR trigger) certifies its review via the hosted notary at https://app.cludbug.dev by default — it submits an attestation bundle with clud-bug post-check-run --sha ... --bundle bundle.json rather than self-attesting. Toggle via "notary": false in .claude/skills/.clud-bug.json (falls back to the labeled self-attested check); override the origin with CLUD_BUG_NOTARY_URL.

For agent invocations of the clud-bug CLI, prefer CLUD_BUG_QUIET=1 (or pass --quiet) — suppresses progress chatter and emits a single ok <key-value> summary line per command.

Installed at clud-bug v0.7.0-rc.20.

<!-- clud-bug-end -->

Read the thread, not the issue body

In several open issues the body describes a design that was superseded in that issue's own comments. Building from the body ships the wrong thing — always read the full comment thread before implementing.

The live answer is the latest maintainer ruling dated on or after the 2026-08-01 SPEC 2.0 merge. Recency alone is not the test: a comment can be the newest one on an issue and still predate the merge that invalidated it (#256 below is exactly this), and not every comment is a ruling.

Confirmed cases:

  • #260 — body asks to add a trust parameter to the probe surface; its comment says delete the probe surface entirely (the body's version is behaviour SPEC 2.0 §4.7 now bans).
  • #256 — has exactly one comment, dated 2026-07-31, so it is both the newest and pre-merge. It cites an intermediate ruling that never shipped, so the fix text it recommends is wrong. Neither the body nor the comment is live: ask before implementing this one.
  • #246 — body, first comment, and last comment each disagree with the one before it; only the 2026-08-01 comment is live.
  • #262 item 7 — duplicates #267.
  • #264 — its body quotes §4.7 backwards, as opt-in with "absent means the reviewer reads none." The merged SPEC says the opposite: on by default, absent means every check. Filed ~2.5 hours before the rewrite landed, so the body was never wrong — it aged out. Bodies do that; comments do not update them.
  • clud-bug-app#87 — its P0 design is now half-MUST, half-FORBIDDEN. The 2026-08-01 comment supersedes the body: rebuild it on CI evidence, not on the probe surface §4.7 bans.
  • clud-bug-app#14 — milder, but the body's framing was reworked in its own comments. Read them before acting on it.

This list is a snapshot, not a guarantee. It was assembled by reading every open issue on 2026-08-01; an issue that acquires a superseding comment tomorrow will not appear here. The rule above is what protects you — the list only names the cases already known to trip it.

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