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/mappamind/mappamind/agents-mdgit clone --depth 1 https://github.com/mappamind/mappamindWhat 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 | $0.00980 | $0.00980 |
| Opus 5 | $0.00490 | $0.00490 |
| Sonnet 5 | $0.00196 | $0.00196 |
| Haiku 4.5 | $0.00098 | $0.00098 |
Grade A, and why
mappamind 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 2d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Mappamind is an open-source TypeScript/ESM npm workspace. Source lives in packages/*/src: capture for file/git evidence, extractors for language facts, baseline for grounded models, seam for contracts, impact for blast radius, synthesis for Claude-backed synthesis, store/ledger for persistence, pipeline for CLI/composition, and core for shared types/config. Tests sit beside source as *.test.ts. See docs/ARCHITECTURE.md for design and architecture context.
Build, Test, and Development Commands
npm installinstalls workspace dependencies. Use Node 20+.npm run buildrunstsc -bacross the project references and emitsdist/.npm testbuilds, then runsnode --testagainst compiledpackages/**/dist/**/*.test.js.npm run cleanremoves TypeScript build outputs viatsc -b --clean.mappamind status <root>reports repo/workspace discovery, baseline freshness, Studio URL, and duplicate hook warnings.mappamind setup <root> --host claude --yesruns the first grounded baseline with Claude Code and writes.mappamind/index.html. Use--host codexwhen running setup through Codex.- Package-local commands, such as
npm test -w @mappamind_/impact, run one workspace after build output exists.
synthesis shells out to claude -p, so related workflows require a local Claude CLI setup.
Coding Style & Naming Conventions
Use strict TypeScript with NodeNext modules and explicit .js extensions in relative imports. Prefer named exports from src/index.ts barrels. Follow existing formatting: two-space indentation, double quotes, semicolons, camelCase values, PascalCase types, and descriptive filenames. Shared primitives belong in @mappamind_/core.
Testing Guidelines
Tests use Node's built-in node:test with node:assert/strict. Name tests *.test.ts next to the code they cover, and assert exact behavior. Add or update tests for changes to extraction, grounding, seam detection, impact computation, persistence, or CLI rendering. Run npm test before handing off.
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.
- 2d ago First seen · 38 lines · 980 tokens per session scan A 4fb3caf17387
mappamind AGENTS.md is an instructions file published in the GitHub repository mappamind/mappamind (3 stars, last pushed 2mo ago), licensed MIT. It adds 980 tokens to every session, about $0.0049 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
claude-code-tresor CLAUDE.md
Instructions for alirezarezvani/claude-code-tresor, covering claude.md - development guide, 🎯 repository purpose, 🏗️ architecture, 🛠️ common development commands and building & testing.
pitway CLAUDE.md
Instructions for thixpin/pitway: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. The project's full instructions live in AGENTS.md — this file only points there so the two can never drift apart.
skills AGENTS.md
Instructions for vanducng/skills, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and documentation sync.
KDD AGENTS.md
Instructions for MauricioPerera/KDD: Este repositorio usa la metodología KDD (Knowledge-Driven Development). Las reglas obligatorias completas están en .agents/AGENTS.md y la skill local en .agents/skills/kdd-okf-ccdd-hybrid/SKILL.md.
avvarre CLAUDE.md
Instructions for PralhadYadawad/avvarre, covering avvarre — claude code instructions, what is avvarre?, available slash commands, mcp tools and project memory (.avvarre/).
AmbyKit CLAUDE.md
Instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.