Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/anselmoo/mcp-server-analyzer/claude-mdgit clone --depth 1 https://github.com/Anselmoo/mcp-server-analyzerWrote 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/anselmoo/mcp-server-analyzer/claude-md)<a href="https://agentmods.dev/instructions/anselmoo/mcp-server-analyzer/claude-md"><img src="https://agentmods.dev/badge/instructions/anselmoo/mcp-server-analyzer/claude-md.svg" alt="Measured on agentmods" 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 | $0.00796 | $0.00796 |
| Opus 5 | $0.00398 | $0.00398 |
| Sonnet 5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
mcp-server-analyzer 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 6d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server Analyzer — Claude Instructions
Branch Naming
- All branches must follow
<type>/<kebab-case-description>(e.g.docs/update-biome-support). check-branch-name: "true"stays enabled in.github/workflows/ci-cd.yml— do NOT set it tofalse.- Worktrees created by Kepler may have non-conventional names (e.g.
update-docs-for-biome). Before creating a PR, rename the worktree branch to follow the convention, or CI will fail. Usegit branch -m <old> <type>/<new>thengit push origin -u <type>/<new>.
repo-release-tools (rrt)
- Pre-commit hooks:
rrt-branch-name(pre-commit),rrt-commit-subject(commit-msg),rrt-changelog(pre-commit). - All three rrt hooks rely on git internals (
git diff --cached, branch name) that are unreliable inpre-commit run --all-filesmode. CI skips all rrt hooks viaSKIP: rrt-branch-name,rrt-commit-subject,rrt-changelogin thelintjob. - Release policy is enforced instead by the dedicated parallel
release-policyjob (runsAnselmoo/[email protected]action) on PRs and tags. Thetestjob waits for bothlintandrelease-policy. - Pin to the latest tagged version — check installed version with
uv run rrt --versionand updaterev:in.pre-commit-config.yamlto match. - Dependabot keeps the CI action (
Anselmoo/[email protected]) up to date automatically — do not pin it manually.
Useful rrt commands
uv run rrt branch new <type> "<description>" # create conventional branch
uv run rrt git commit "<description>" # conventional commit (infers type from branch)
uv run rrt changelog lint # lint [Unreleased] entries for style
uv run rrt bump patch # bump patch version across all targets
uv run rrt doctor # project health check
uv run rrt release check # validate version targets and changelog
GitHub / PR Creation
ghCLI does not work in this environment (missing token). Usemcp__GitKraken__pull_request_createor the GitHub MCP tool instead.- Target branch for PRs:
main.
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.
- 6d ago First seen · 46 lines · 796 tokens per session scan A 6369ccfb0d5e
mcp-server-analyzer CLAUDE.md is an instructions file published in the GitHub repository Anselmoo/mcp-server-analyzer (11 stars, last pushed 6d ago), licensed MIT. It adds 796 tokens to every session, about $0.0040 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
copilot-mcp AGENTS.md
AGENTS.md instructions for VikashLoomba/copilot-mcp, covering agents.md, engineering standard, project shape, build + run and ui testing requirements.
copilot-mcp CLAUDE.md
Claude Code instructions for VikashLoomba/copilot-mcp, covering claude.md, project overview, development commands, root directory commands and install dependencies for both extension and web ui.
getspecstory copilot-instructions.md
Copilot instructions for specstoryai/getspecstory: Examine the file changes for the pull request.
memorix CLAUDE.md
Claude Code instructions for AVIDS2/memorix, covering memorix - agent instructions for claude code, using memorix memory tools, when to search memory, when to store memory and when to resolve memory.
memorix GEMINI.md
Gemini CLI instructions for AVIDS2/memorix, covering memorix - cross-agent memory rules, session start - bind project, then load context, during session - capture important context, architecture & decisions and bug fixes & problem solving.
bootstrap-alwayson
Minimal always-required LLM fixes.