planning-codebase-changes-with-evidence
Skill1 starsChanged 3 months agoMITView on GitHub
Use when you need a change evidence brief to inform another method's executable plan for a real codebase change.
In this repository65 other files it gives its agents.
- analyzing-change-blast-radiusSkill
- analyzing-developer-career-opportunitiesSkill
- art-directing-web-interfacesSkill
- assessing-developer-proficiencySkill
- auditing-dependency-riskSkill
- auditing-pixel-perfect-frontendSkill
- bootstrapping-modern-web-appsSkill
- brag-slimSkill
- building-brand-guidelinesSkill
- building-conversion-product-pagesSkill
- building-developer-career-roadmapsSkill
- building-hybrid-game-assetsSkill
- building-premium-nextjs-interfacesSkill
- building-project-showcasesSkill
- building-regression-testsSkill
- building-reliable-node-api-boundariesSkill
- choosing-application-architectureSkill
- craft-premium-motionSkill
- creating-character-sprite-pipelinesSkill
- defining-brand-strategySkill
- designing-action-combatSkill
- designing-developer-portfolio-evidenceSkill
- designing-relational-data-modelsSkill
- designing-software-boundariesSkill
- designing-test-strategiesSkill
- designing-ui-systemsSkill
- designing-visual-identitiesSkill
- documenting-architecture-decisionsSkill
- editing-for-clarity-and-toneSkill
- engineering-gsap-animationsSkill
- evaluating-developer-proficiencySkill
- evolving-postgres-schemas-safelySkill
- humanizing-generated-proseSkill
- implementing-reference-faithful-uiSkill
- investigating-codebase-semanticallySkill
- managing-implementation-slicesSkill
- mapping-existing-codebase-structureSkill
- naming-brands-and-productsSkill
- optimizing-frontend-motion-performanceSkill
- orchestrating-cinematic-web-motionSkill
- planning-engineering-workSkill
- planning-launch-distributionSkill
- planning-safe-refactorsSkill
- planning-written-communicationSkill
- preparing-project-launchSkill
- profiling-postgres-query-performanceSkill
- reconstructing-images-as-threejsSkill
- reviewing-api-securitySkill
- reviewing-apple-platform-interfacesSkill
- reviewing-pull-requestsSkill
- reviewing-web-securitySkill
- selecting-working-methodsSkill
- shipping-github-vercel-changesSkill
- teaching-developer-conceptsSkill
- testing-integration-boundariesSkill
- testing-playable-gamesSkill
- testing-web-applications-end-to-endSkill
- threat-modeling-applicationsSkill
- tracing-code-execution-pathsSkill
- translating-figma-to-nextjsSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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 14
Ask one narrow structural question, define its scope, and state the decision it supports.
- Distinctive: line 16
Use the narrowest symbol, relation, or targeted search that can answer the question.
- Distinctive: line 17
Use an explicit fallback when runtime evidence is unavailable or inconclusive: inspect targeted symbols, search, imports, references, …
- Very specific: line 18
Keep an evidence ledger for every material claim: claim, status (observed, inferred, or unresolved), source, location, confidence, and …
- Distinctive: line 19
Stop at sufficiency when traceable evidence answers the question, critical dependencies are checked, gaps are classified, and further …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
Ownership
Produce a change evidence brief for another planning method; do not execute the implementation plan.
The workflow below implements the shared Codebase Intelligence evidence contract.
Workflow
- Ask one narrow structural question, define its scope, and state the decision it supports.
- Detect whether an optional code-intelligence runtime is available through callable tools only. Do not install a runtime, do not run
codegraph init, and do not create.codegraph/without explicit authorization. - Use the narrowest symbol, relation, or targeted search that can answer the question; expand only to close a named evidence gap.
- Use an explicit fallback when runtime evidence is unavailable or inconclusive: inspect targeted symbols, search, imports, references, tests, configuration, and direct reads. A textual match is not proof of a caller, callee, or owner.
- Keep an evidence ledger for every material claim: claim, status (
observed,inferred, orunresolved), source, location, confidence, and relevance. - Stop at sufficiency when traceable evidence answers the question, critical dependencies are checked, gaps are classified, and further reading is unlikely to change the immediate decision. Hand off to the next owner.
Output contract
- objective;
- explicit in/out scope;
- current-state evidence;
- affected surfaces;
- relevant paths and contracts;
- risks;
- unresolved questions;
- suggested slices;
- testing surfaces;
- handoff to Architecture, Engineering Workflow, Quality & Testing, or Systematic Debugging;
Does not own
Executable planning, implementation, TDD, or slice management; do not implement the plan. Hand executable planning to Engineering Workflow or writing-plans.
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.

