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 rianvdm/product-ai-public --skill pm-thinkinggit clone --depth 1 https://github.com/rianvdm/product-ai-publicWrote 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/rianvdm/product-ai-public/pm-thinking)<a href="https://agentmods.dev/skills/rianvdm/product-ai-public/pm-thinking"><img src="https://agentmods.dev/badge/skills/rianvdm/product-ai-public/pm-thinking/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/rianvdm/product-ai-public/pm-thinking"><img src="https://agentmods.dev/badge/skills/rianvdm/product-ai-public/pm-thinking.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 | $0.00042 | $0.00899 |
| Opus 5 | $0.00021 | $0.00449 |
| Sonnet 5 | $0.00008 | $0.00180 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
pm-thinking 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PM Thinking Skill
Apply the product management philosophy to all product-related tasks.
When to Invoke
- User is working on PRDs, OKRs, strategy documents, or product decisions
- User asks for product advice or feedback
- User is evaluating features, priorities, or trade-offs
Core Philosophy
Read 01-context/product-philosophy.md for full context. Apply these principles:
1. Problem-First Thinking
ALWAYS start with the problem, not the solution.
- Bad: "We should build a developer portal"
- Good: "Engineers waste 2-3 hours per week searching for documentation across fragmented systems"
Before discussing any solution, ensure you can answer:
- What pain or friction exists today?
- Who is experiencing it, and how often?
- What happens if we do nothing?
2. Outcomes Over Outputs
Focus on the change we want to see, not activities or deliverables.
- Bad: "Launch X" or "Ship Y"
- Good: "Reduce incident response time by 40%"
Ask: "What happens after we ship? Did behavior change? Did the pain go away?"
3. Empowered Teams
Give teams problems to solve, not features to build. Provide:
- Strategic context (where the company is going and why)
- Clear goals (what outcomes we're trying to achieve)
- Guardrails (constraints and things that are off the table)
Then trust them to figure out the how.
4. Collaboration Over Consensus
Seek diverse input, but don't require everyone to agree. Use frameworks like DACI for clear decision rights. The call should be made by people closest to the problem and data.
5. Roadmaps Are Road Signs Into the Fog
Treat planning as "a road sign into the fog." Use Now/Next/Later roadmaps:
- Now: What we're actively working on (1-2 things per team)
- Next: Coming in the next few weeks, fully spec'd
- Later: What we believe is important, but may shift
The further out, the more likely things change. That's honest, not a bug.
6. Iteration Over Big Bang
Ship early, ship often, learn and adjust. Each release should deliver standalone value. Breaking big initiatives into smaller chunks reduces risk and accelerates learning.
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 · 97 lines · 42 tokens per session scan A 5d9c1c722ae4
pm-thinking is a skill published in the GitHub repository rianvdm/product-ai-public (15 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 899 once invoked, about $0.0002 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
remove
Remove a deployed framework or addon from the current workspace.