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/professorpalmer/puppetmaster/agents-mdgit clone --depth 1 https://github.com/professorpalmer/PuppetmasterWhat 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 | $0.04520 | $0.04520 |
| Opus 5 | $0.02260 | $0.02260 |
| Sonnet 5 | $0.00904 | $0.00904 |
| Haiku 4.5 | $0.00452 | $0.00452 |
Grade A, and why
Puppetmaster 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repo-level guidance for AI coding agents (Cursor, Claude Code, Codex, etc.) working in this repository. Cursor users see the same directive via .cursor/rules/puppetmaster-workflow.mdc.
First: are you a Puppetmaster worker?
If your prompt was issued by Puppetmaster, everything below about starting a swarm does not apply to you. You are the swarm. Do the analysis or the edit yourself, directly, and return the artifacts your prompt asks for.
You are a Puppetmaster worker if your prompt contains any of:
- a
Puppetmaster artifact contract:/Return only Puppetmaster artifact JSONblock, - a
Role: <role>+Goal: <goal>header, - an instruction to finish by calling
submit_findingsorsubmit_report.
Workers are spawned by puppetmaster.worker_runtime as plain agent CLIs. They
have no Puppetmaster MCP tools, so "start a swarm before exploring" is an
instruction they cannot follow — following it costs a full context load and
returns a request for clarification instead of findings. Roll your own
grep/read loop; that is your job.
The rest of this file addresses an interactive agent working with the user,
which has the MCP tools available. Pi is in that class: a TUI/pilot via the bundled @puppetmaster/pi-pilot package (puppetmaster install-pi-mcp / setup --platforms pi). OMP / oh-my-pi is the same class via native MCP (puppetmaster install-omp-mcp / setup --platforms omp or ohmypi; writes ~/.omp/agent/mcp.json). Use start_implement / start_agentic / start_prewalk, consume artifacts, nuke the job. Do not lease pi or omp as a worker.
Default subagent runtime: Puppetmaster
When this repo is open — and you are not a Puppetmaster worker (see above) — Puppetmaster's MCP tools are the primary path for fanning out work. Do not roll your own grep/read exploration loops or invoke ad-hoc subagents when a Puppetmaster swarm is available.
When to start a Puppetmaster swarm (do this by default)
For any request that involves more than a single trivial change, start a Puppetmaster swarm before spending tokens on your own exploration:
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 · 204 lines · 4,520 tokens per session scan A 3ff5bb80bc8e
Puppetmaster AGENTS.md is an instructions file published in the GitHub repository professorpalmer/Puppetmaster (349 stars, last pushed 3d ago), licensed MIT. It adds 4,520 tokens to every session, about $0.0226 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 2026-08-30.
Other instructions, from other repositories
codedb AGENTS.md
AGENTS.md instructions for justrach/codedb, covering codedb agent guidelines, what codedb is (and isn't), review guidelines, pre-merge verification and security-sensitive areas.
honey-for-devs copilot-instructions.md
Instructions for Green-PT/honey-for-devs, covering honey (i shrunk the ai), intensity, lever 1 — minimum code that needs to exist, never cut (lazy ≠ broken) and lever 2 — say less about it.
claude-code-blueprint CLAUDE.md
Instructions for faizkhairi/claude-code-blueprint, covering global claude behavior rules, verify-after-complete (mandatory), what to verify depends on what was built, verification mindset and after verification.
claude-code-blueprint AGENTS.md
Instructions for faizkhairi/claude-code-blueprint, covering agents.md: repository orientation for ai assistants, what this repo is, what this repo is not, repository layout and how to help the user.
agent-native-setup AGENTS.md
Instructions for luca-mastrostefano/agent-native-setup, covering agent-native-setup — agent contract, navigation and command surface.
agent-skills AGENTS.md
Instructions for powabase-ai/agent-skills, covering agents.md, repository structure, prerequisites & commands, writing skill.md files and frontmatter (required).