celestial-skills / code-review-engineering
AGENTS.md1 starsChanged 18 days agoApache-2.0View on GitHub
Review a pull request in a fixed order, from whether it is correct to whether it is tested, so real problems are caught and feedback is clear enough to act on. Generated from the Celestial engineering practice “Code review”.
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 repository182 other files it gives its agents.
- skills/accessibility-audit-engineering/AGENTS.mdAGENTS.md
- skills/angular-app-engineering/AGENTS.mdAGENTS.md
- skills/aspnet-core-api-engineering/AGENTS.mdAGENTS.md
- skills/chrome-extension-engineering/AGENTS.mdAGENTS.md
- skills/ci-cd-pipelines-engineering/AGENTS.mdAGENTS.md
- skills/compose-android-app-engineering/AGENTS.mdAGENTS.md
- skills/context-engineering-engineering/AGENTS.mdAGENTS.md
- skills/database-migrations-engineering/AGENTS.mdAGENTS.md
- skills/dbt-analytics-engineering/AGENTS.mdAGENTS.md
- skills/dependency-supply-chain-engineering/AGENTS.mdAGENTS.md
- skills/deprecation-and-removal-engineering/AGENTS.mdAGENTS.md
- skills/design-tokens-to-code-engineering/AGENTS.mdAGENTS.md
- skills/django-app-engineering/AGENTS.mdAGENTS.md
- skills/end-to-end-testing-engineering/AGENTS.mdAGENTS.md
- skills/expo-react-native-app-engineering/AGENTS.mdAGENTS.md
- skills/fastapi-service-engineering/AGENTS.mdAGENTS.md
- skills/fastify-api-engineering/AGENTS.mdAGENTS.md
- skills/feature-flags-engineering/AGENTS.mdAGENTS.md
- skills/flutter-app-engineering/AGENTS.mdAGENTS.md
- skills/framework-upgrades-engineering/AGENTS.mdAGENTS.md
- skills/git-workflow-engineering/AGENTS.mdAGENTS.md
- skills/go-http-service-engineering/AGENTS.mdAGENTS.md
- skills/graphql-api-engineering/AGENTS.mdAGENTS.md
- skills/incident-response-engineering/AGENTS.mdAGENTS.md
- skills/incremental-implementation-engineering/AGENTS.mdAGENTS.md
- skills/internationalisation-engineering/AGENTS.mdAGENTS.md
- skills/kubernetes-helm-engineering/AGENTS.mdAGENTS.md
- skills/laravel-app-engineering/AGENTS.mdAGENTS.md
- skills/launch-readiness-engineering/AGENTS.mdAGENTS.md
- skills/llm-features-and-evals-engineering/AGENTS.mdAGENTS.md
- skills/marketing-site-engineering/AGENTS.mdAGENTS.md
- skills/nestjs-service-engineering/AGENTS.mdAGENTS.md
- skills/nextjs-app-engineering/AGENTS.mdAGENTS.md
- skills/nuxt-app-engineering/AGENTS.mdAGENTS.md
- skills/observability-engineering/AGENTS.mdAGENTS.md
- skills/privacy-by-design-engineering/AGENTS.mdAGENTS.md
- skills/python-ml-service-engineering/AGENTS.mdAGENTS.md
- skills/rails-app-engineering/AGENTS.mdAGENTS.md
- skills/react-web-app-engineering/AGENTS.mdAGENTS.md
- skills/release-and-versioning-engineering/AGENTS.mdAGENTS.md
- skills/requirements-interview-engineering/AGENTS.mdAGENTS.md
- skills/rest-api-design-engineering/AGENTS.mdAGENTS.md
- skills/rust-axum-service-engineering/AGENTS.mdAGENTS.md
- skills/rust-cli-tool-engineering/AGENTS.mdAGENTS.md
- skills/safe-refactoring-engineering/AGENTS.mdAGENTS.md
- skills/secure-code-review-engineering/AGENTS.mdAGENTS.md
- skills/source-grounded-development-engineering/AGENTS.mdAGENTS.md
- skills/spec-before-code-engineering/AGENTS.mdAGENTS.md
- skills/spec-driven-development-engineering/AGENTS.mdAGENTS.md
- skills/spring-boot-service-engineering/AGENTS.mdAGENTS.md
- skills/sveltekit-app-engineering/AGENTS.mdAGENTS.md
- skills/swiftui-ios-app-engineering/AGENTS.mdAGENTS.md
- skills/systematic-debugging-engineering/AGENTS.mdAGENTS.md
- skills/task-breakdown-engineering/AGENTS.mdAGENTS.md
- skills/tauri-desktop-app-engineering/AGENTS.mdAGENTS.md
- skills/technical-documentation-engineering/AGENTS.mdAGENTS.md
- skills/terraform-infrastructure-engineering/AGENTS.mdAGENTS.md
- skills/test-first-development-engineering/AGENTS.mdAGENTS.md
- skills/threat-modelling-engineering/AGENTS.mdAGENTS.md
- skills/typescript-library-engineering/AGENTS.mdAGENTS.md
- The first 60 shown.
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Distinctive: line 26
Treat any new endpoint, permission check or dependency as blocking until reviewed explicitly.
- Distinctive: line 27
Leave style and formatting to automated tools.
- Distinctive: line 28
Ask what happens when each external call fails or times out.
≈ “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 — Code review
Review a pull request in a fixed order, from whether it is correct to whether it is tested, so real problems are caught and feedback is clear enough to act on.
How to do it
- Read the intent first — Read the linked issue, description and acceptance criteria before the diff. If you cannot say in one sentence what the change should do, ask before reviewing.
- Check size and scope — If the diff is over about 400 changed lines or mixes unrelated changes, ask for it to be split before a detailed review.
- Verify correctness — Trace the main path and each edge case: empty input, nulls, limits, concurrency, failure of every external call. Run the branch or the preview link when behaviour is user-visible.
- Check security — Look for unvalidated input, injection, missing authorisation checks, secrets in code or logs, unsafe deserialisation and new dependencies with known issues.
- Judge design and readability — Is the code in the right module, with clear names and boundaries? Could a new teammate change it safely? Flag duplication of existing helpers.
- Check performance — Look for queries in loops, unbounded lists, missing pagination or indexes, large bundle additions and work on hot paths.
- Check the tests — Confirm tests cover new behaviour and error paths and would fail if the code were wrong. Mentally flip a condition and ask whether any test catches it.
- Write the review — Label each comment as blocking, suggestion or question, explain why, and propose a fix where you can. Approve only when every blocking item is resolved.
Checklist (before a pull request)
- The change does what the issue asks, including stated edge cases
- No input reaches a query, shell, template or file path without validation
- No secrets, tokens or personal data appear in code, tests or logs
- New behaviour and failure paths have tests that would catch a regression
- Names, module placement and boundaries match the surrounding code
- Every comment is labelled blocking, suggestion or question
- CI is green on the final commit that was reviewed
Rules
- Review the behaviour, not the author; phrase comments about the code. (People act on feedback that does not feel personal.)
- Treat any new endpoint, permission check or dependency as blocking until reviewed explicitly. (These are the changes most likely to open a vulnerability.)
- Leave style and formatting to automated tools; do not spend review comments on them. (Human attention is the scarce resource in review.)
- Ask what happens when each external call fails or times out. (Unhandled failures are the most common gap in otherwise correct code.)
- Request evidence, such as a query plan or benchmark, when a change touches a hot path. (Performance claims without measurement are guesses.)
Checks
| Gate | Tool | Threshold | When |
| Required approval | Branch protection on the main branch | At least one approving review from someone other than the author; all blocking comments resolved | Every pull request |
Generated from the Celestial engineering practice “Code review”.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

