claude-code-primitives
Skill40 starsChanged 39 days agoMITView on GitHub
Reference for Claude Code's own mechanics — slash commands, skills, subagents, hooks — and how they route together. Use when creating or editing a slash command, skill, subagent, or hook, or when deciding which primitive fits a task.
In this repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- branch-preflightSkill
- cleaning-up-merged-branchesSkill
- diagnoseSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- improve-codebase-architectureSkill
- inkwell-retrofitSkill
- open-knowledgeSkill
- pb-collectionSkill
- reviewable-pr-slicingSkill
- setup-matt-pocock-skillsSkill
- shadcnSkill
- shipSkill
- source-command-build-nextSkill
- source-command-qcheckSkill
- source-command-triage-prsSkill
- to-issuesSkill
- verify-frontend-changeSkill
- branch-preflightSkill
- cleaning-up-merged-branchesSkill
- inkwell-retrofitSkill
- pb-collectionSkill
- reviewable-pr-slicingSkill
- verify-frontend-changeSkill
- verify-gsdSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Agent teams vs subagents: Use subagents for scoped delegation inside one workstream.
≈ “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
Claude Code Primitives
- Routing: Commands initiate, subagents verify, hooks gate.
- Slash Commands (
.claude/commands/): Short, repeatable actions. Canonical text of prompts lives here (e.g.,/qspec,/tdd,/qcheck). - Skills (
.claude/skills/): Complex multi-step workflows. Write descriptions as triggers ("when should I fire?"). Provide goals, constraints, and a "Gotchas" section. - Subagents (
.claude/agents/): Spawn for fanning out or parallel reads. Skip for <3 tool calls. Read-only agents usehaiku; write agents usesonnet/opuswithisolation: worktree. - Agent teams vs subagents: Use subagents for scoped delegation inside one workstream. Use teams when work should split across longer-lived sessions that coordinate.
- Hooks: Enforce standards mechanically (e.g.,
PostToolUse,Stop). Hook types: shell commands, prompt hooks, MCP tool hooks. - Hooks receive event data as JSON on stdin. Read fields with
jq, for example.tool_input.file_path; do not rely on$CLAUDE_FILE_PATHstyle variables unless explicitly configured.
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.