Borrowing it
Nothing to install: this file belongs to GMRoadlander/llm-wiki-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/GMRoadlander/llm-wiki-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/GMRoadlander/llm-wiki-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/gmroadlander/llm-wiki-mcp/claude-md)<a href="https://agentmods.dev/instructions/gmroadlander/llm-wiki-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/gmroadlander/llm-wiki-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/gmroadlander/llm-wiki-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/gmroadlander/llm-wiki-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 | $0.00844 | $0.00844 |
| Opus 5 | $0.00422 | $0.00422 |
| Sonnet 5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
llm-wiki-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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
llm-wiki-mcp
An MCP server (plus an Agent SDK companion) for Gil's LLM_Wiki — the LLM-maintained second-brain vault at ~\ClaudeProjects\LLM_Wiki\. Built to be used every day, not to sit in a repo.
Standing bar (Gil, 2026-07-25): self-sustaining and not shoddy. This code will be read by strangers and must survive expert review. Quality is a feature, not overhead.
Phase 0 — prior-art audit (BEFORE any design or code)
Web-verify the existing landscape: MCP servers for Obsidian/markdown vaults and note systems (official and community). For each relevant one: what tools it exposes, how it handles config/safety, what's weak. Output: docs/prior-art.md with (a) what we adopt from them, (b) what we deliberately do differently and why (this vault's capture/ingest/lint/crystallize conventions are the differentiator). If an existing server genuinely covers the need, say so — the decision to build anyway must be reasoned in writing, not assumed.
Phase 1 — MCP server v1 (Python, official mcp SDK / FastMCP)
Tools (v1 scope — small and real; resist scope creep):
search_wiki(query, limit)— full-text + filename search across the vaultread_note(path)— return a note's content + frontmatterlist_recent(n)— recently modified noteswrite_note(path, content, mode)— gated:appendandcreateonly; never destructive overwrite; dry-run flagget_links(path)— outbound links / backlinks for a note
Non-negotiables:
- Config, not hardcode: vault path via env var / config file. No usernames or machine paths in code.
- Safety: path-traversal guard (every resolved path must stay inside the vault root); reads are default, writes explicitly gated; malformed/missing notes return clean errors, never tracebacks.
- Typed, tested: type hints throughout; pytest suite against a synthetic fixture vault in
tests/fixtures/(never real vault content); tests cover the traversal guard, malformed frontmatter, empty vault, and unicode. - Tooling: ruff (lint + format) clean;
pyproject.tomlwith pinned deps; CHANGELOG.md; semver tags from v0.1.0.
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.
- 2d ago Changed · +15 tokens per session d363eb182861
- 8d ago First seen · 45 lines · 829 tokens per session scan A d7c84beb9417
llm-wiki-mcp CLAUDE.md is an instructions file published in the GitHub repository GMRoadlander/llm-wiki-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 844 tokens to every session, about $0.0042 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.