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/blueprint-chart/mcp/agents-mdgit clone --depth 1 https://github.com/blueprint-chart/mcpWhat 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 | $0.01597 | $0.01597 |
| Opus 5 | $0.00798 | $0.00798 |
| Sonnet 5 | $0.00319 | $0.00319 |
| Haiku 4.5 | $0.00160 | $0.00160 |
Grade A, and why
mcp AGENTS.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 yesterday.
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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@blueprint-chart/mcp — Coding Guidelines
General
- TypeScript everywhere, strict mode.
- Small, iterative, semantic commits — no co-author or body. Conventional types only:
feat,fix,refactor,test,chore,docs,style. - Makefile targets are the canonical way to run operations (
make install,make dev,make test,make lint,make build). - Code quality and readability are central — keep tools, resources, and render modules small and single-purpose.
- This package follows the same conventions as
blueprint-chart. Where this file is silent, defer to that one.
Project Structure
Single-package npm project (@blueprint-chart/mcp) — no workspace, no Vue, no SCSS.
src/
server.ts # Transport-agnostic MCP Server; wires tools, resources, prompts
cli.ts # CLI entry: stdio default, --http for hosted; reads env vars
parse.ts # parseDsl: wraps @blueprint-chart/lib's Peggy parser with ToolResult
errors.ts # ErrorCode enum + ToolResult<T> shape
tools/ # Tool handlers: validate, inspect, recommend, render
resources/ # Resource handlers: docs-backed + samples-backed
prompts/ # Prompt templates (author_chart)
render/ # Headless render pipeline (jsdom + textShim + resvg)
transports/ # stdio + StreamableHTTP entries; share `createServer()`
lib/ # Internal helpers (e.g. zod→JSON Schema stub)
bin/
blueprint-chart-mcp.js # CLI launcher
loader.mjs # ESM resolver hook (resolves extensionless imports)
test/
integration/ # In-memory MCP transport tests, transport-parity
golden/ # Render snapshot suite over @blueprint-chart/lib samples
docs/superpowers/ # Local-only spec/plan artifacts (gitignored)
Dependencies
Pinned npm packages (no workspace deps):
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.
- yesterday First seen · 130 lines · 1,597 tokens per session scan A 68c6556fe61f
mcp AGENTS.md is an instructions file published in the GitHub repository blueprint-chart/mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 1,597 tokens to every session, about $0.0080 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
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.