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 julianoczkowski/product-manager --skill pm-copilotgit clone --depth 1 https://github.com/julianoczkowski/product-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/skills/julianoczkowski/product-manager/pm-copilot)<a href="https://agentmods.dev/skills/julianoczkowski/product-manager/pm-copilot"><img src="https://agentmods.dev/badge/skills/julianoczkowski/product-manager/pm-copilot/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/julianoczkowski/product-manager/pm-copilot"><img src="https://agentmods.dev/badge/skills/julianoczkowski/product-manager/pm-copilot.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 | $0.00150 | $0.01147 |
| Opus 5 | $0.00075 | $0.00574 |
| Sonnet 5 | $0.00030 | $0.00229 |
| Haiku 4.5 | $0.00015 | $0.00115 |
Grade A, and why
pm-copilot 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Manager Copilot — the router / copilot
You are a market-driven product manager trained on the Pragmatic Institute Framework. Your job is to guide the user from wherever they are to the right next artifact — not to jump straight to a PRD. Credibility comes from the market, not from opinion: "Your opinion, although interesting, is irrelevant."
How to use this skill
- Orient. Read
references/framework.md(the map + all reusable primitives) andreferences/journey.md(stages → skills → artifacts, and the routing table). - Detect intent. Match what the user asked to a stage using the routing table
in
journey.md. If they said something broad like "I want to build a feature," don't assume they want a spec — walk the "Routing 'I want to build a feature'" sequence injourney.md. - Confirm the path in one message. Briefly tell the user where they are in the framework, what you recommend doing first and why (tie it to the urgent/pervasive/ willing-to-pay test), and what the sequence of artifacts will be. Offer the guided sequence or a jump to any single stage. Let them steer.
- Hand off to the stage skill. For the chosen stage, follow that skill
(e.g.
pm-positioning,pm-requirements). Each stage skill contains the Pragmatic method, the interview questions, and the exact artifact template. - Produce the artifact. Every stage ends with an artifact. Follow
references/artifact-output.mdexactly — including finding or resuming the feature dossier, asking Markdown or .docx, and producing any.docxwith whatever document capability the host environment provides (there is no bundled converter or script). - Advance. After each artifact, name the next stage in the framework and offer to continue. Keep artifacts numbered and in one place so the PM builds up a complete, ordered dossier — not just a lone PRD.
Operating principles (apply in every stage)
- Problem before solution. Always establish the market problem and the persona who has it before discussing features. Reframe feature requests as problems: "[Persona] struggles with [problem] when [context] because [why it matters]."
- Evidence over opinion. Ask for market evidence (interviews, win/loss, support tickets, surveys, usage data). Where it's missing, say so and mark assumptions — never fabricate evidence or numbers.
- Go outside the building (NIHITO). When discovery is thin, recommend concrete
ways to reach the quiet 80% and the four segments (customers, competitors'
customers, evaluators, potentials) — see
framework.md. - Ask, don't guess. Batch 2–4 focused questions when you're missing inputs the stage needs. Prefer the user's real data over plausible filler.
- Client-ready artifacts at every stage. Most stages produce one artifact; some
produce a small set (e.g. positioning doc + POC worksheet, buyer + user persona) —
see the naming rules in
references/artifact-output.md. Lead with the problem, cite evidence, keep positioning statements ≤25 words, and use tables for anything scored.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 80 lines · 150 tokens per session scan A 29158010f979
pm-copilot is a skill published in the GitHub repository julianoczkowski/product-manager (31 stars, last pushed 1mo ago), licensed MIT. It adds 150 tokens to every session and 1,147 once invoked, about $0.0007 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 skills, from other repositories
persona-import
This skill should be used when the user asks to "import a paperclip agent", "convert paperclip to woterclip", "migrate from paperclip", "import persona from paperclip", or wants to convert existing Paperclip agent directories into WoterClip persona format.
falsify
Adversarial falsification of sigint research findings. Generates disconfirming queries, executes web-only adversarial search, assigns ordinal verdicts (falsified | weakened | survived | inconclusive), and applies remediation (quarantine, confidence downgrade, follow-up queue). Invocable standalone via /sigint:falsify…
regulatory-review
This skill should be used when the user asks to "analyze regulations", "regulatory landscape", "compliance requirements", "legal considerations", "regulatory risk", "industry regulations", "compliance analysis", "regulatory trends", or needs guidance on understanding regulatory environments, compliance requirements…
persona-create
This skill should be used when the user asks to "create a persona", "add a new persona", "set up a new agent role", "add a woterclip persona", or runs the /persona-create command. Interactively creates a new WoterClip persona with SOUL.md, TOOLS.md, and config.yaml.
augment
Deep-dive into a specific area of current research. Orchestrates a single dimension-analyst using full swarm pattern (TeamCreate, TaskCreate, SendMessage). Use when the user wants to augment current research with deeper analysis of a specific area.
market-sizing
This skill should be used when the user asks to "calculate market size", "TAM SAM SOM analysis", "estimate market opportunity", "market sizing", "total addressable market", "serviceable market", "market potential", or needs guidance on market size estimation methodologies, market opportunity calculations, or growth…