kit
CLAUDE.md0 starsChanged 11 days agoMITView on GitHub
Read AGENTS.md first: what Kit is, the commands, the TUI rules. The product plan is docs/PRD.md; the bar for every change is docs/QUALITY.md. Project skills live in .claude/skills/ (Kit-specific, written for this repo). Engineering skills live in .agents/skills/ (vendored from addyosmani/agent-skills, MIT, © 2025 Addy Osmani; licence in .agents/skills/LICENSE-addyosmani-agent-skills, pins in skills-lock.json).
In this repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- api-and-interface-designSkill
- browser-testing-with-devtoolsSkill
- ci-cd-and-automationSkill
- code-review-and-qualitySkill
- code-simplificationSkill
- context-engineeringSkill
- debugging-and-error-recoverySkill
- deprecation-and-migrationSkill
- documentation-and-adrsSkill
- doubt-driven-developmentSkill
- frontend-ui-engineeringSkill
- git-workflow-and-versioningSkill
- idea-refineSkill
- incremental-implementationSkill
- interview-meSkill
- observability-and-instrumentationSkill
- performance-optimizationSkill
- planning-and-task-breakdownSkill
- security-and-hardeningSkill
- shipping-and-launchSkill
- source-driven-developmentSkill
- spec-driven-developmentSkill
- test-driven-developmentSkill
- using-agent-skillsSkill
- kit-ci-triageSkill
- kit-evalsSkill
- kit-provider-adaptersSkill
- kit-releaseSkill
- kit-tuiSkill
- a11y-passSkill
- add-readmeSkill
- api-docsSkill
- changelogSkill
- cli-helpSkill
- code-reviewSkill
- completeness-qaSkill
- data-checkSkill
- deps-hygieneSkill
- fix-bugSkill
- project-setupSkill
- pr-readySkill
- ship-checklistSkill
- workspace-setupSkill
- write-testsSkill
The file
We split this CLAUDE.md into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 3
Read AGENTS.md first: what Kit is, the commands, the TUI rules.
- Distinctive: line 32
Never print or commit a key or token.
- Distinctive: line 33
Commit as the owner's identity configured in the repo.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
Kit — instructions for Claude Code
Read AGENTS.md first: what Kit is, the commands, the TUI rules. The product plan is
docs/PRD.md; the bar for every change is docs/QUALITY.md.
Skills: when to use which
Project skills live in .claude/skills/ (Kit-specific, written for this repo). Engineering skills live in
.agents/skills/ (vendored from addyosmani/agent-skills,
MIT, © 2025 Addy Osmani; licence in .agents/skills/LICENSE-addyosmani-agent-skills, pins in
skills-lock.json).
| When you are… | Use | Where |
Changing anything under crates/kit-tui or anything that draws to the terminal | kit-tui | .claude/skills |
| Adding or changing a model provider or an agent driver (Claude Code, Codex, Grok, ACP) | kit-provider-adapters | .claude/skills |
| Changing the agent loop, a tool, a prompt or a provider, or quoting a benchmark | kit-evals | .claude/skills |
| Bumping a version, editing the changelog, tagging, reading a release run | kit-release | .claude/skills |
| A CI check failed, or you need build/test proof (especially on Windows) | kit-ci-triage | .claude/skills |
| Starting a new feature or milestone | spec-driven-development → planning-and-task-breakdown | .agents/skills |
| Implementing | incremental-implementation, test-driven-development | .agents/skills |
| A bug, a flaky test, a wrong output | debugging-and-error-recovery | .agents/skills |
A public contract (--json, KIT.toml, kit.toml, receipts, traits) | api-and-interface-design | .agents/skills |
| Sandbox, permissions, keys, hooks, anything security-relevant | security-and-hardening | .agents/skills |
| Cold start, idle CPU, render cost | performance-optimization | .agents/skills |
| Before opening a PR | code-review-and-quality, code-simplification | .agents/skills |
| A boundary decision worth recording | documentation-and-adrs (ADRs in docs/adr/) | .agents/skills |
Always
- Prove it:
cargo fmt --all --check,cargo clippy --workspace --all-targets -- -D warnings,cargo test --workspace, andrust.ymlgreen on Ubuntu, macOS and Windows. "Looks right" is not done. - Never print or commit a key or token. Never tag, publish or run a paid eval without the owner.
- Commit as the owner's identity configured in the repo; end messages with the attribution the session gives.
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.