agent-reviews
AGENTS.md299 starsChanged 30 days agoMITView on GitHub
CLI + Agent Skills for managing GitHub PR review comments. See README.md for full details.
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 31,542 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 repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- resolve-agent-reviewsSkill
- resolve-human-reviewsSkill
- resolve-reviewsSkill
The file
We split this AGENTS.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
- Distinctive: line 29
No em dashes: Use commas, periods, or parentheses instead.
- Very specific: line 34
Changelog: when shipping a new version, add an entry to both README.md (under ## Changelog) and website/src/lib/components/Changelog.svelte …
≈ “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.
Files
AGENTS.md
Project
CLI + Agent Skills for managing GitHub PR review comments. See README.md for full details.
Structure
bin/agent-reviews.js CLI entry point (npm -g users)
lib/ Core modules (github, comments, format)
skills/resolve-reviews/ Skill: all reviews (human + bot)
skills/resolve-agent-reviews/ Skill: bot reviews only
skills/resolve-human-reviews/ Skill: human reviews only
.claude-plugin/ Plugin manifest + marketplace catalogKey Commands
| Task | Command |
| Install skills locally | npm run install-skills (also runs on npm install) |
| Publish to npm | npm publish |
| Test CLI locally | node bin/agent-reviews.js |
| Run tests | npm test |
Rules
- No em dashes. Use commas, periods, or parentheses instead.
- Node.js CommonJS throughout (no ESM) applies to runtime code in
bin/,lib/, andscripts/. Tests and tooling may use ESM when required by their framework. - Version in three places:
package.json,.claude-plugin/plugin.json,skills/*/SKILL.mdfrontmatter. - Skills use
npx agent-reviews(no bundled scripts). - No status messages, only results applies to
--jsonoutput. Human-readable CLI output may include concise status messages. - Changelog: when shipping a new version, add an entry to both
README.md(under## Changelog) andwebsite/src/lib/components/Changelog.svelte(newchangelog-entrydiv at the top of the list). Keep entries concise, one<li>per feature/fix.
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
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.