MDCP
CLAUDE.md2 starsChanged 5 days agoMITView on GitHub
You are working in MDCP (Master Developer Claude Plugin). MDCP supports provider routing for compatible API clients through configured gateways such as OmniRoute. The optional free-llm-switcher.js module is for a separately running Node.js application that has provider API keys. Important boundaries: Do not promise infinite loops, uninterrupted execution, autonomous background work, or automatic model switching inside Claude.ai.
In this repository108 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/composition-patterns/AGENTS.mdAGENTS.md
- skills/react-best-practices/AGENTS.mdAGENTS.md
- skills/react-view-transitions/AGENTS.mdAGENTS.md
- skills/master-developer/references/CLAUDE.mdCLAUDE.md
- agent-fabricSkill
- api-anythingSkill
- creator-security-automationSkill
- feature-implementationSkill
- omniroute-free-llm-routingSkill
- repository-auditSkill
- security-reviewSkill
- unslopSkill
- youtube-studioSkill
- agent-developmentSkill
- agent-fabricSkill
- agent-security-hardeningSkill
- algorithmic-artSkill
- api-anythingSkill
- api-designSkill
- backend-patternsSkill
- brand-guidelinesSkill
- build-mcp-appSkill
- build-mcpbSkill
- build-mcp-serverSkill
- canvas-designSkill
- claude-apiSkill
- claude-md-improverSkill
- coding-standardsSkill
- command-developmentSkill
- vercel-composition-patternsSkill
- creator-security-automationSkill
- database-migrationsSkill
- deployment-patternsSkill
- dispatching-parallel-agentsSkill
- docker-patternsSkill
- e2e-testingSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- frontend-a11ySkill
- frontend-designSkill
- frontend-patternsSkill
- hook-developmentSkill
- master-developerSkill
- mcp-builderSkill
- mcp-dependency-reviewSkill
- mcp-integrationSkill
- mdcp-self-checkSkill
- mdcp-token-meterSkill
- nextjs-turbopackSkill
- omniroute-free-llm-routingSkill
- plugin-settingsSkill
- plugin-structureSkill
- postgres-patternsSkill
- prisma-patternsSkill
- vercel-react-best-practicesSkill
- vercel-react-view-transitionsSkill
- receiving-code-reviewSkill
- replica-architectSkill
- replica-backendSkill
- The first 60 shown.
The file
We split this CLAUDE.md into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
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
- could be automatic: a setting could enforce it
- Distinctive: line 10
Use filesystem and Git tools only when the host actually provides them.
- Distinctive: line 11
Never commit API keys, tokens, private checkpoints, or user secrets.
- Distinctive: line 12
Run relevant tests, validation, lint, and type checks.
- Distinctive: line 13
Do not push, publish, merge, delete, or change repository visibility unless the user explicitly authorizes that action.
- Distinctive: line 33
Run targeted tests and repository validation.
- Distinctive: line 37
Do not promise infinite loops, uninterrupted execution, autonomous background work, or automatic model switching inside Claude.ai.
≈ “Common” is an estimate: at least 1 in 5 of the 27,641 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
MDCP — Claude-compatible workspace instructions
You are working in MDCP (Master Developer Claude Plugin).
Repository rules
- Inspect existing implementation and tests before editing.
- Preserve existing architecture and third-party licenses. Do not claim bundled third-party code is exclusively owned by this repository's author.
- Make the smallest complete change. Do not invent implemented feature counts, agents, routes, or integrations.
- Use filesystem and Git tools only when the host actually provides them. Instructions cannot grant tools, background execution, MCP access, or GitHub permissions.
- Never commit API keys, tokens, private checkpoints, or user secrets.
- Run relevant tests, validation, lint, and type checks. Report actual commands and outcomes; never claim zero warnings without running them.
- Do not push, publish, merge, delete, or change repository visibility unless the user explicitly authorizes that action.
Provider fallback
MDCP supports provider routing for compatible API clients through configured gateways such as OmniRoute. The optional free-llm-switcher.js module is for a separately running Node.js application that has provider API keys.
Important boundaries:
- Claude.ai usage limits are enforced by Anthropic. Prompts, Artifacts, MCP memory, or this repository cannot bypass those limits.
- Claude.ai does not automatically execute external API calls when its hosted model limit is reached.
- Fallback works only when an independent client/agent calls the configured provider API.
- Free provider tiers are quota-limited, may require API keys, and can change model availability or terms.
- A successful fallback response is not proof that a coding task was implemented. The caller must apply changes, run tests, inspect diffs, and save checkpoints.
- Checkpoints are local application files, not Claude Memory or automatic GitHub commits.
Task workflow
- Inspect relevant files and current Git state.
- Prepare a short plan.
- Implement a focused patch.
- Run targeted tests and repository validation.
- Inspect the final diff for regressions and secrets.
- Report changed files, test results, limitations, and manual setup.
Do not promise infinite loops, uninterrupted execution, autonomous background work, or automatic model switching inside Claude.ai.
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.

