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 skills add professorpalmer/Puppetmaster --skill puppetmaster-pilotgit 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/skills/professorpalmer/puppetmaster/puppetmaster-pilot)<a href="https://agentmods.dev/skills/professorpalmer/puppetmaster/puppetmaster-pilot"><img src="https://agentmods.dev/badge/skills/professorpalmer/puppetmaster/puppetmaster-pilot/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/skills/professorpalmer/puppetmaster/puppetmaster-pilot"><img src="https://agentmods.dev/badge/skills/professorpalmer/puppetmaster/puppetmaster-pilot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.00224 |
| Opus 5.5 | $0.00020 | $0.00090 |
| Sonnet 5.5 | $0.00010 | $0.00045 |
| Haiku 4.5 | $0.00005 | $0.00022 |
Grade A, and why
puppetmaster-pilot 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.
What it actually says
Puppetmaster from Pi
Pi stays the TUI / head seat. Never lease pi as a Puppetmaster worker
adapter. Spawn disposable Puppetmaster jobs; consume artifacts, not
transcripts; size the runtime; nuke the job.
Verbs
- Coupled multi-file feature:
puppetmaster_start_implement - Keys-only contained path:
puppetmaster_start_implementwithadapter: "agentic" - Size / preflight the work:
puppetmaster_route_task - Recall:
puppetmaster_show - Status:
puppetmaster_status/puppetmaster_artifactswith refs - Done:
puppetmaster gcthe finished job. Do not keep workers alive.
Do not read worker transcripts. Prefer compact refs and show.
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 5919c33ec84f
- 1mo ago First seen · 23 lines · 49 tokens per session scan A 96567acf5a7e
puppetmaster-pilot is a skill published in the GitHub repository professorpalmer/Puppetmaster (469 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 224 once invoked, about $0.0002 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 skills, from other repositories
honey-px
Read huge read-only text as PNG pages; big input cut.
honey-debt
Harvest honey shortcut markers into a debt ledger.
cast-mod
Make a codecast mod, a small sandboxed module that adds panes, commands and new kinds of blocks agents can draw to the codecast app, and that reads the person's sessions, tasks, plans, PRs and more. Use when asked to customize, extend, retheme or add something to codecast's interface, to build a dashboard or view over…
orchestrate
Drive a plan to completion by orchestrating implementer, reviewer, and critic agents across waves of parallel work. Use when the user says "orchestrate", "implement this plan", "execute plan", "drive this", or approves a plan for execution.
cast-plan
Turn a request into a plan the team can review before code exists. Explores the codebase, searches prior sessions and recorded decisions for earlier attempts, interviews the user on the open questions, then writes a codecast plan with tasks and dependencies ready for orchestrate. Use when work has several parts, when…
cast-pass
Hand this session to a teammate so it lands in their inbox with everything they need. Pins where the work stands and what is next, adds them as an owner, and sends them the brief. Use when work should continue under someone else, when a decision is theirs, or when asked to pass, hand over, or assign a session.