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/wernerglinka/metalsmith-plugin-mcp-server/claude-mdgit clone --depth 1 https://github.com/wernerglinka/metalsmith-plugin-mcp-serverWrote 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/wernerglinka/metalsmith-plugin-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/wernerglinka/metalsmith-plugin-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/wernerglinka/metalsmith-plugin-mcp-server/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 | $0.01636 | $0.01636 |
| Opus 5 | $0.00818 | $0.00818 |
| Sonnet 5 | $0.00327 | $0.00327 |
| Haiku 4.5 | $0.00164 | $0.00164 |
Grade A, and why
metalsmith-plugin-mcp-server 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 5d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metalsmith Plugin MCP Server — Development Context
This file gives Claude what it needs to work in this repo. Project overview, release notes, and migration steps live in README.md, CHANGELOG.md, RELEASE.md, and MIGRATION.md respectively — don't duplicate them here.
Composes with ~/Documents/CLAUDE.md (loaded by Claude Code under ~/Documents/).
Tone rules from there apply: direct, no agreement filler, prose over bullets,
no em-dashes.
Hard rules
Never modify configuration files without explicit permission
Includes any .json, .yml, .yaml, .config.js. Always ask:
"Should I modify [file] to [change]?"
The trap to remember: .release-it.json has "npm.publish": false
intentionally. Werner publishes to npm manually. Do not flip this to true.
Detect context before invoking MCP tools
Run LS first. Files present (package.json, src/, README.md) → existing
project; use get-template, validate, install-claude-md, edit files
directly. Empty directory → new project; use plugin-scaffold. Never call
plugin-scaffold against a populated directory.
Never mock Metalsmith in tests
Use a real Metalsmith instance against a temp directory. Applies to tests
in this repo and to scaffolded plugin test templates. Mocking
metalsmith(), metalsmith.match, metalsmith.debug, metalsmith.env,
metalsmith.path, or plugin invocation has historically hidden signature
mismatches, metadata bugs, and path resolution errors that only surfaced in
production. Metalsmith lives in devDependencies for this reason. Mocking
unrelated systems (network, non-Metalsmith fs concerns) is fine.
Follow MCP server recommendations verbatim
When the MCP server returns a recommendation, copy the suggested code or configuration exactly. Do not paraphrase, "simplify", or improvise an equivalent. Past Claude instances have done this and broken release workflows.
Pre-commit workflow
Before any commit or release, run in order:
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.
- 5d ago First seen · 181 lines · 1,636 tokens per session scan A 62df041679ba
metalsmith-plugin-mcp-server CLAUDE.md is an instructions file published in the GitHub repository wernerglinka/metalsmith-plugin-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,636 tokens to every session, about $0.0082 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
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).
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 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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.