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.
git clone --depth 1 https://github.com/professorpalmer/PuppetmasterWrote 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/rules/professorpalmer/puppetmaster/puppetmaster-workflow)<a href="https://agentmods.dev/rules/professorpalmer/puppetmaster/puppetmaster-workflow"><img src="https://agentmods.dev/badge/rules/professorpalmer/puppetmaster/puppetmaster-workflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/professorpalmer/puppetmaster/puppetmaster-workflow"><img src="https://agentmods.dev/badge/rules/professorpalmer/puppetmaster/puppetmaster-workflow.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02448 | $0.02448 |
| Opus 5.5 | $0.00979 | $0.00979 |
| Sonnet 5.5 | $0.00490 | $0.00490 |
| Haiku 4.5 | $0.00245 | $0.00245 |
Grade A, and why
puppetmaster-workflow 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 10d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
First: are you a Puppetmaster worker?
If your prompt was issued by Puppetmaster, none of the "start a swarm" guidance below applies to you. You are the swarm. Do the analysis or the edit yourself and return the artifacts your prompt asks for.
You are a Puppetmaster worker if PUPPETMASTER_WORKER=1, or your prompt contains
a Puppetmaster artifact contract: block, a Role: <role> + Goal: <goal>
header, or an instruction to finish by calling submit_findings /
submit_report. Workers run as plain agent CLIs with no Puppetmaster MCP
tools, so delegating is impossible; attempting it burns the context window and
returns a clarifying question instead of findings. Nested job starts
(python -m puppetmaster swarm, MCP start verbs) are refused while that env is
set. Override: PUPPETMASTER_ALLOW_NESTED=1. Roll your own grep/read loop —
that is your job.
The rest of this file addresses an interactive agent working with the user, which does have the MCP tools.
Puppetmaster is the fan-out runtime
When this repo is open, and you are not a Puppetmaster worker (see above), work solo unless parallel workers clearly finish sooner or better. When work fans out, Puppetmaster is the path, not ad-hoc subagents.
When to start a Puppetmaster swarm
Start one when the work splits into independent units that each take a worker minutes, or when there is more of it than one session can finish well:
- Broad investigation, audit, or risk analysis across many areas (independent read-only lenses in parallel).
- Many independent modules or files to build or change: one flow
(
puppetmaster_flow) with groupedmapitems, per-unit checks and, for craft-graded output, a render check plus a rubric judge. - Comparing approaches when independent candidates help.
The default routing is:
- Call
puppetmaster_start_cursor_swarm(read-only multi-role analysis) — this is the daily-driver entry point. - For implementation that needs durable patches, logs, and dirty-tree guards, use
puppetmaster_start_implementin a clean worktree — it routes to whatever platform the lock enables (cursor preferred, then claude-code).puppetmaster_start_cursor_implement/puppetmaster_start_claude_implementforce a specific platform. - For a single fast review or plan pass,
puppetmaster_start_cursor_review/puppetmaster_start_cursor_planare acceptable lighter alternatives.
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.
- 10d ago Changed · +2 lines · -1 tokens per session 62baf9843448
- 1mo ago Changed · +3 lines · +48 tokens per session c7ffc4aab9e8
- 1mo ago First seen · 133 lines · 2,401 tokens per session scan A 1ac4d852116f
puppetmaster-workflow is a cursor rule published in the GitHub repository professorpalmer/Puppetmaster (468 stars, last pushed yesterday), licensed MIT. It adds 2,448 tokens to every session, about $0.0098 per session on Opus 5.5. 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 cursor rules, from other repositories
research-before-suggesting
Never make up features, APIs, or config options. Research before suggesting technical solutions.
agent-models
Which model subagents use. Default is the parent's model; the user's most recent instruction overrides it.
conservative-file-creation
Check for existing files before creating. Be conservative about new files and code.
repository-layout
Canonical map of repo folders and docs.
engineering-standards
Engineering quality — security defaults, show options when planning, think through failure modes.
x402-coding
@dexterai/x402 SDK conventions and hosted-only OpenDexter tool usage.