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/becrafter/prompt-manager/agents-mdgit clone --depth 1 https://github.com/BeCrafter/prompt-managerWrote 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/becrafter/prompt-manager/agents-md)<a href="https://agentmods.dev/instructions/becrafter/prompt-manager/agents-md"><img src="https://agentmods.dev/badge/instructions/becrafter/prompt-manager/agents-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 | $0.09435 | $0.09435 |
| Opus 5 | $0.04718 | $0.04718 |
| Sonnet 5 | $0.01887 | $0.01887 |
| Haiku 4.5 | $0.00944 | $0.00944 |
Grade C, and why
prompt-manager AGENTS.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf node_modules package-lock.json How it starts
The opening of the file, as written. The whole thing — 1,224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Codebase Guide for AI Agents
Project Overview
- Type: Monorepo-like structure (manual orchestration, no workspaces)
- Language: JavaScript (ES Modules with .js extensions)
- Node.js: v22.20.0+ required (see .nvmrc)
- Type Safety: Zod schemas for runtime validation (no TypeScript)
Build, Lint & Test Commands
Development Commands
npm run dev # Start all services (backend + admin + desktop) - RECOMMENDED
npm run dev:backend # Backend server with --watch (port 5621)
npm run dev:admin # Admin UI webpack dev server (port 9000)
npm run dev:desktop # Electron desktop app
Build Commands
npm run build # Build all (admin-ui + core)
npm run build:core # Build server package (esbuild)
npm run build:admin-ui # Build admin UI (webpack → packages/web/)
npm run build:desktop # Build desktop app (current platform)
npm run build:desktop:all # Build desktop for all platforms (mac/win/linux)
npm run build:icons # Build app icons
Linting & Formatting
npm run lint # Run ESLint with auto-fix
npm run lint:fix # Run ESLint with auto-fix
npm run lint:check # Check ESLint without fixing
npm run format # Run Prettier to format code
npm run format:fix # Run Prettier with auto-fix
npm run format:check # Check formatting without changing files
Test Commands
npm test # Run ALL tests (verification + server + integration)
npm run test:server # Server unit tests only
npm run test:server:watch # Watch mode for unit tests
npm run test:server:coverage # Generate coverage report (70% threshold)
npm run test:server:integration # Server integration tests
npm run test:e2e # E2E tests for packaged app
npm run test:module-loading # Module loading tests
Verification Commands
npm run verify # Run comprehensive publish verification (recommended before commits)
npm run verify:publish # Verify npm package publish readiness
npm run check:deps # Check and install all dependencies
npm run check:env # Check development environment
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 · 1,224 lines · 9,435 tokens per session scan C ce3b66bcc320
prompt-manager AGENTS.md is an instructions file published in the GitHub repository BeCrafter/prompt-manager (16 stars, last pushed 5mo ago), licensed MIT. It adds 9,435 tokens to every session, about $0.0472 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
oh-my-posh AGENTS.md
AGENTS.md instructions for JanDeDobbeleer/oh-my-posh, covering agent instructions, project overview, tech stack, key commands and go - run from src/.
oh-my-posh copilot-instructions.md
Copilot instructions for JanDeDobbeleer/oh-my-posh: All agent guidance for this repository lives in AGENTS.md: project overview, key commands, architecture orientation, coding and commit conventions, skills, and the project-knowledge workflow. Follow it in full.
oh-my-posh markdown.instructions.md
Instructions for JanDeDobbeleer/oh-my-posh: Refer to skills/markdown/SKILL.md for the full Markdown formatting standards.
oh-my-posh powershell.instructions.md
Instructions for JanDeDobbeleer/oh-my-posh: Refer to skills/powershell/SKILL.md for the full PowerShell coding standards.
plano CLAUDE.md
Instructions for katanemo/plano, covering claude.md, build & test commands, rust — wasm plugins (must target wasm32-wasip1), rust — brightstaff binary (native target) and rust — tests, format, lint.
llm-exe CLAUDE.md
Claude Code instructions for llm-exe/llm-exe, covering llm-exe — claude code context, philosophy, guiding principles, feature evaluation — read this before adding features and how it works.