celestial-skills / incremental-implementation-engineering
AGENTS.md1 starsChanged 18 days agoApache-2.0View on GitHub
Build in thin vertical slices that each compile, pass tests and get committed, so you always have a working save point and any mistake costs one small revert. Generated from the Celestial engineering practice “Incremental implementation”.
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/code-review-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/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
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 25
Never have more than one failing test or broken thing at a time.
- Distinctive: line 26
Commit after every green slice, and never commit red.
≈ “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 — Incremental implementation
Build in thin vertical slices that each compile, pass tests and get committed, so you always have a working save point and any mistake costs one small revert.
How to do it
- Pick one slice — Take the next task from the plan and define the smallest piece of behaviour that works end to end. Write down the check that will prove it: usually one test.
- Start from green — Run the build and tests before changing anything. If they already fail, stop and report or fix that first; never start a slice on a red baseline.
- Make one thing fail — Add or change a single test for the slice and watch it fail for the expected reason. Keep only one failing thing at a time.
- Make it pass with a small diff — Write the least code that turns that test green without breaking others. Defer cleanup and generalisation to a later step.
- Run the full checks — Run lint, type checks and the relevant test suite. The slice is not done until all of them pass.
- Commit a checkpoint — Commit the green slice with a message naming the task or requirement ID. Each commit is a save point you can return to. Hide unfinished user-facing behaviour behind a feature flag so the commit could ship.
- Tidy, then commit again — Refactor with tests green, as a separate commit. Never mix behaviour changes and cleanup in one commit.
- Stop and report when stuck — If a slice is still red after a few focused attempts or a set time box, revert to the last checkpoint and report: the goal, what was tried, the exact failure output and a proposed next step. Do not pile on further changes.
Checklist (before a pull request)
- The baseline was green before the first change
- Every commit compiles and passes lint, types and tests
- No commit contains more than one slice of behaviour
- Behaviour changes and refactors are in separate commits
- Unfinished user-facing behaviour is behind a flag that defaults off
- Any slice that could not be made green was reverted and reported
- The pull request diff is small enough to review in one sitting
Rules
- Never have more than one failing test or broken thing at a time. (With one failure, the cause is the last change; with several, you are debugging combinations.)
- Commit after every green slice, and never commit red. (Green checkpoints make rollback a single revert and keep bisecting useful.)
- Roll back by reverting the slice's commit, not by hand-editing code back. (A revert is exact and recorded; manual undo leaves fragments behind.)
- Build the error and empty states in their own slices, each with a test. (Edge cases added at the end tend to be skipped under deadline.)
- Ship schema changes as additive slices before the code that uses them, and remove old columns in a later slice. (Each step stays deployable and reversible on its own.)
Checks
| Gate | Tool | Threshold | When |
| Green commits | CI run on every pushed commit | Every commit in the pull request passes lint, types and tests | Every push |
| Small diffs | Pull request size check | Under 400 changed lines; no single commit over 200 | Every pull request |
Generated from the Celestial engineering practice “Incremental implementation”.
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.

