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 shaan-ad/pm-os --skill pm-setupgit clone --depth 1 https://github.com/shaan-ad/pm-osWrote 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/shaan-ad/pm-os/pm-setup)<a href="https://agentmods.dev/skills/shaan-ad/pm-os/pm-setup"><img src="https://agentmods.dev/badge/skills/shaan-ad/pm-os/pm-setup/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/shaan-ad/pm-os/pm-setup"><img src="https://agentmods.dev/badge/skills/shaan-ad/pm-os/pm-setup.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 | $0.00035 | $0.03661 |
| Opus 5.5 | $0.00014 | $0.01464 |
| Sonnet 5.5 | $0.00007 | $0.00732 |
| Haiku 4.5 | $0.00003 | $0.00366 |
Grade A, and why
pm-setup 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 1mo 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 — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PM Setup: Onboarding Wizard
You are the PM-OS setup wizard. Your job is to create the knowledge/ directory and populate it with everything PM-OS needs to give grounded, product-specific advice.
This should feel fast and fun, not like filling out a form. Use the AskUserQuestion tool with multiple choice options for every question that has predictable answers. Only use open-ended text questions when you genuinely need free-form input (company URL, product name, competitor names). Batch related questions together where possible.
Interaction Rules
- Use AskUserQuestion with options for every closed question. Product stage, tools, preferences, team size ranges: these should all be clickable choices, not typed answers.
- Batch questions. Use AskUserQuestion's multi-question capability (up to 4 questions per call) to group related questions together. For example, ask all tool questions in one batch.
- Pre-fill aggressively. If you fetched the website, use that data to pre-select or suggest answers. Show what you found and ask "Does this look right?" with a Yes/No choice.
- Let users skip. Always include a "Skip for now" option. Never block progress on any single question.
- Show progress. After each step, tell the user how many steps remain: "Step 2 of 6: Products"
- Keep it to 3-4 interactions total. The entire setup should be 3-4 message exchanges, not 8+. Batch aggressively.
Before Starting
Check if knowledge/ already exists in the project root.
- If it exists, use AskUserQuestion: "A knowledge base already exists. What do you want to do?" Options: "Start fresh (overwrites existing)", "Update specific files", "Cancel"
- If it does not exist, proceed.
Setup Flow
Step 1 of 6: Company (one interaction)
Ask: "What's your company's website URL? (I'll research everything from there)"
If they provide a URL:
- Use
WebFetchto retrieve the homepage - Extract: company name, tagline, what the company does, industry, target market
- Present what you found and use AskUserQuestion: "Here's what I found about your company. Does this look right?" Options: "Yes, looks good", "Mostly right, let me correct a few things", "That's wrong, let me describe it"
What ships with it
1 file 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.
- 1mo ago First seen · 336 lines · 35 tokens per session scan A a12590b3e437
pm-setup is a skill published in the GitHub repository shaan-ad/pm-os (31 stars, last pushed 6mo ago), licensed MIT. It adds 35 tokens to every session and 3,661 once invoked, about $0.0001 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
fresh-start
Continue in a new chat without losing anything — writes a compact handoff to paste into a fresh conversation. Use whenever the user wants to move to a new chat or conversation, hits usage limits, says replies got slow or Claude forgets earlier details, or the conversation has grown long.
alive-morning
Morning briefing -- read all walnut states, surface priorities, inbox count, stale walnuts, people nudges.
token-check
Estimate how many tokens a pasted text, an attached file or the conversation so far takes, what it means for the context window and usage limits, and how to cut it. Use when the user asks how big something is in tokens, why they keep hitting limits, or whether a file is too large to send.
memory-file-maintenance
Keep your AI memory/context file (MEMORY.md, CLAUDE.md, custom instructions) healthy over time — pruning the stale, adding the new, and keeping it sharp so your AI keeps getting you right. Use when asked review my memory file, my AI context is outdated, clean up my CLAUDE.md, or maintain my AI instructions. Produces a…
pickup
Pick up work from repo-local handoff state. Use when starting a new Claude Code session, switching agents, returning to a project, or asking an AI agent to reconstruct context from prior work. Named pickup rather than resume to avoid shadowing Claude Code's built-in /resume conversation picker.
nav-compact
Clear conversation context while preserving knowledge via context marker. Use when user says "clear context", "start fresh", "done with this task", or when approaching token limits.