Borrowing it
Nothing to install: this file belongs to olafgeibig/knowledge-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/olafgeibig/knowledge-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/olafgeibig/knowledge-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/olafgeibig/knowledge-mcp/claude-md)<a href="https://agentmods.dev/instructions/olafgeibig/knowledge-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/olafgeibig/knowledge-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/olafgeibig/knowledge-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/olafgeibig/knowledge-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00359 | $0.00359 |
| Opus 5.5 | $0.00144 | $0.00144 |
| Sonnet 5.5 | $0.00072 | $0.00072 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
knowledge-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Ignore Patterns
CLAUDE.md .aider* attic/ docs/
Coding
- Use Python 3.12 features and syntax
- Follow PEP 8 style guide for Python code
- Use type hints everywhere possible
- Use list, dict, and set comprehensions when appropriate for concise and readable code.
- Prefer pathlib over os.path for file system operation
- Use explicit exception handling. Catch specific exceptions rather than using bare except clauses
- Keep functions and methods small and focused on a single task
- Use docstrings for all public modules, functions, classes, and methods
- Use dataclasses for data containers when appropriate
- Prefer composition over inheritance where possible
- Use logging for debugging and monitoring
- Use meaningful variable and method names
Development
- Use pytest for unit testing
- Do not create tests unless requested by the user
- Use uv for dependency management
Using uv
- use 'uv add ' to add dependencies
- use 'uv remove ' to remove dependencies
- Create uv scripts for running scripts in pyproject.toml [project.scripts]
- Use hatchling as the build-system
Running
- Ensure activate the venv before spawning a new console session:
source .venv/bin/activate - Use uv scripts to run something
Using Tools (MCP)
- Use the sequential-thinking tool if the problem is complex and you need to think hard, you need to think step by step. This is mandatory.
- Use the context7 tool to look up the documentation of a library.
Project
- Project sepecification is in the specs directory:
- prd.md: project requirements
- plan.md: development plan
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 43 lines · 359 tokens per session scan A b12ef2508f53
knowledge-mcp CLAUDE.md is an instructions file published in the GitHub repository olafgeibig/knowledge-mcp (59 stars, last pushed 8mo ago), licensed MIT. It adds 359 tokens to every session, about $0.0014 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
knowledge-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| knowledge-mcp CLAUDE.mdolafgeibig/knowledge-mcp | Instructions file | 59 | 8mo ago | MIT | A | 359 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |