claude-toolkit
llms.txt4 starsChanged 3 months agoMITView on GitHub
An opinionated Claude Code and Cursor configuration that enforces engineering discipline — TDD, signed commits, worktree isolation, and an agentic engine (kickoff enrichment, a recommendation panel, a goal evaluator) — through hooks and skills.
Files
llms.txt
# claude-toolkit > An opinionated Claude Code and Cursor configuration that enforces > engineering discipline — TDD, signed commits, worktree isolation, and an > agentic engine (kickoff enrichment, a recommendation panel, a goal > evaluator) — through hooks and skills. ## Docs - [README](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/README.md): documentation index - [Getting Started](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/getting-started.md): prerequisites, installation, first workflow - [Engineering Discipline](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/engineering-discipline.md): the six enforced ideas and their implementations - [Architecture](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/architecture.md): coordination-branch/worktree architecture, plus the agentic engine - [Graphify Code Graph](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/graphify.md): install the graphifyy CLI, build a repo graph, query it before grepping - [Claude Code Configuration](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/claude-code.md): hooks, settings, plugins, policies - [Cursor Configuration](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/cursor.md): agents, commands, rules, hooks - [Deployment Scripts](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/deployment.md): deploy.sh, capture.sh, diff.sh - [Skills & Commands Reference](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/skills-and-commands.md): every slash command and skill - [Skill README Template](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/skill-readme-template.md): SKILL.md vs README.md standard - [Testing Agent Models](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/testing-agent-models.md): verifying Cursor agent model settings - [Agents](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/agents.md): how an agent should traverse this repo's docs - [Orchestration: Loops → Graphs](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/orchestration.md): the prompts → loops → graphs maturity model, mapped to toolkit components ## Patterns - [OpenRouter Free-Tier Backend](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/patterns/openrouter-free-tier.md): running the engine at $0 against OpenRouter's `:free` catalog - [Model ID Hygiene](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/patterns/model-id-hygiene.md): single- vs double-namespace catalog IDs and the sync gate - [Panel Config](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/patterns/panel-config.md): validate-recommendation panel config.yml walkthrough - [Workflow Library](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/patterns/workflow-library.md): reusable named workflow DAGs shipped in .claude/workflows/ — review-verify, chief-dispatch, weekly-audit ## Examples - [Kickoff on OpenRouter](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/examples/kickoff-openrouter.md): live kickoff enrichment run against a `:free` model, with captured output - [Panel on OpenRouter](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/examples/panel-openrouter.md): live validate-recommendation DA panelist dispatch, with captured verdict - [Done on OpenRouter](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/docs/examples/done-openrouter.md): live done goal-evidence evaluation, with captured JSON verdict ## Engine source - [tool.kickoff](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/.claude/tool/kickoff.py): kickoff enrichment - [tool.backends](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/.claude/tool/backends.py): the provider seam (build_chat_model / invoke_llm) - [panel.dispatch](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/.claude/skills/validate-recommendation/panel/dispatch.py): validate-recommendation panel dispatch - [done evaluator](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/.claude/skills/done/eval.py): session-goal evidence evaluation - [panel config template](https://raw.githubusercontent.com/ArangoGutierrez/claude-toolkit/main/.claude/panel/config.yml.template): panelist config template
In this repository48 other files it gives its agents.
- .claude/templates/AGENTS.mdAGENTS.md
- docs/agents.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- .cursor/rules/core.mdcCursor rule
- .cursor/rules/go.mdcCursor rule
- .cursor/rules/k8s.mdcCursor rule
- .cursor/rules/node.mdcCursor rule
- .cursor/rules/python.mdcCursor rule
- .cursor/rules/rust.mdcCursor rule
- .cursor/rules/tdd.mdcCursor rule
- .cursor/rules/workbench.mdcCursor rule
- llms-full.txtllms.txt
- cmux-sprint-orchestratorSkill
- config-auditSkill
- doneSkill
- eurekaSkill
- goalSkill
- go-reviewSkill
- handoffSkill
- js-reviewSkill
- k8s-debugSkill
- k8s-reviewSkill
- kickoffSkill
- pr-review-ingestSkill
- pr-reviewSkill
- python-reviewSkill
- reflectionSkill
- skill-evalSkill
- tdd-protocolSkill
- team-executeSkill
- team-planSkill
- team-shutdownSkill
- test-reviewSkill
- validate-recommendationSkill
- worktree-guideSkill
- babysitSkill
- canvasSkill
- create-hookSkill
- create-ruleSkill
- create-skillSkill
- create-subagentSkill
- migrate-to-skillsSkill
- sdkSkill
- shellSkill
- split-to-prsSkill
- statuslineSkill
- update-cli-configSkill
- update-cursor-settingsSkill
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.