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/rbsoftwaresystems/draftlytic-mcp/claude-mdgit clone --depth 1 https://github.com/rbsoftwaresystems/draftlytic-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/rbsoftwaresystems/draftlytic-mcp/claude-md)<a href="https://agentmods.dev/instructions/rbsoftwaresystems/draftlytic-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rbsoftwaresystems/draftlytic-mcp/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 | $0.01736 | $0.01736 |
| Opus 5 | $0.00868 | $0.00868 |
| Sonnet 5 | $0.00347 | $0.00347 |
| Haiku 4.5 | $0.00174 | $0.00174 |
Grade A, and why
draftlytic-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 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
draftlytic-mcp is an offline MCP server (stdio transport) that turns a rough project idea into a structured spec (PRD). It is a lite, self-contained version of Draftlytic (GitHub) — the hosted app — packaged as an MCP server. It exposes tools to validate, render, and checklist a spec, plus one prompt to drive the whole flow. No network calls, no API key — the client's model does all the actual writing; this server only supplies schema, validation, and deterministic rendering logic.
Commands
npm run build # tsc compile, src/ -> dist/
npm test # build + node --test test/*.test.mjs (unit + integration suite)
npm run smoke # build + scripts/smoke.mjs (spawns dist/index.js, runs raw MCP initialize/tools-list/prompts-list over stdio, asserts expected tools/prompt are present)
The test suite lives in test/*.test.mjs and uses only Node's built-in runner (node:test + node:assert/strict) — no third-party test dependency, matching the package's dependency-light ethos. Tests import from the compiled dist/ output (same convention as scripts/smoke.mjs), so npm test builds first. test/fixtures.mjs provides shared spec factories (validSpec() — zero validation issues, minimalValidSpec() — valid but triggers all quality hints, clone()). One test file per src/ module plus test/index.test.mjs, which spawns the built server and drives the real tool/prompt handlers over stdio. smoke remains the lighter pre-publish sanity check; prepublishOnly runs build before every npm publish. When changing tool/prompt registration in src/index.ts, update EXPECTED_TOOLS/the prompt check in scripts/smoke.mjs and the assertions in test/index.test.mjs if names change.
To exercise the server manually against a real MCP client, add it as a local path-based server (e.g. claude mcp add draftlytic -- node /path/to/dist/index.js) after building.
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 · 51 lines · 1,736 tokens per session scan A 31dcd34f478e
draftlytic-mcp CLAUDE.md is an instructions file published in the GitHub repository rbsoftwaresystems/draftlytic-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,736 tokens to every session, about $0.0087 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).
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.
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).
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.