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/agent-blueprint/mcp-server/claude-mdgit clone --depth 1 https://github.com/agent-blueprint/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/agent-blueprint/mcp-server/claude-md)<a href="https://agentmods.dev/instructions/agent-blueprint/mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/agent-blueprint/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 | $0.00572 | $0.00572 |
| Opus 5 | $0.00286 | $0.00286 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
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 4d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Agent Blueprint MCP Server
This is the MCP server and CLI for Agent Blueprint. npm package: agentblueprint.
Commands
npm run build # TypeScript compile (tsc)
npm test # Vitest
npm run dev # Watch mode
Architecture
Two entry points, one shared core:
src/cli.ts CLI entry (TTY → help, piped → MCP server)
src/download.ts CLI download handler (writes files to disk)
src/mcp-setup.ts ServiceNow MCP server setup (credentials, install, config)
src/tools/*.ts MCP tool handlers (return JSON manifests)
src/fetch-blueprint.ts SHARED: data fetching + rendering (used by both CLI and MCP)
src/directives.ts SHARED: post-download agent directives (used by both CLI and MCP)
src/renderers.ts Agent Skills renderer (GETTING-STARTED, SKILL.md, all references/)
src/server.ts MCP server setup + tool registration
src/client.ts HTTP client for Agent Blueprint v1 API
src/config.ts Config resolution (flag > env > token store)
src/token-store.ts Persistent token storage
Critical Rules
-
Vendor-agnostic output. All rendered content (
renderers.ts) ships to every customer on every platform. No platform-specific language. No ServiceNow (GlideRecord, sys_app, Agent Studio). No Salesforce. Vendor-specific guidance belongs in expert skills (docs/kb/vendor-skills/in the main app repo), delivered via--platformflag. -
Single source of truth. CLI and MCP tool paths must share logic, not duplicate it.
fetch-blueprint.tshandles data fetching + rendering.directives.tshandles post-download text. If you need to change behavior that affects both paths, change the shared module. Never put the same string or logic in bothdownload.tsandtools/download-blueprint.ts. -
Test before shipping. Run
npm test. All tests must pass. If you add new behavior, add tests.
Publishing
Cannot publish from Claude Code (WebAuthn 2FA). The user runs npm version patch && npm publish manually. Always bump the version before asking the user to publish.
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.
- 4d ago First seen · 47 lines · 572 tokens per session scan A 2a613899bf45
mcp-server CLAUDE.md is an instructions file published in the GitHub repository agent-blueprint/mcp-server (3 stars, last pushed 1mo ago), licensed MIT. It adds 572 tokens to every session, about $0.0029 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
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
flyto-core CLAUDE.md
Claude Code instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.