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 fmind/dot --skill product-managementgit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/product-management)<a href="https://agentmods.dev/skills/fmind/dot/product-management"><img src="https://agentmods.dev/badge/skills/fmind/dot/product-management/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/fmind/dot/product-management"><img src="https://agentmods.dev/badge/skills/fmind/dot/product-management.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 | $0.00020 | $0.00873 |
| Opus 5.5 | $0.00008 | $0.00349 |
| Sonnet 5.5 | $0.00004 | $0.00175 |
| Haiku 4.5 | $0.00002 | $0.00087 |
Grade A, and why
product-management 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 9d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Management
Move a product bet through discovery, specification, launch, and learning. Enter at the phase supported by the evidence and make the next decision; implementation-plan owns repository execution planning.
Workflow
- Recover the bet: user, painful job, proposed outcome, constraints, current evidence, and the decision being made; enter at the phase the evidence supports.
- Challenge the premise: separate observations, supplied evidence, inference, and assumptions; always keep doing nothing, a manual service, or a smaller change among the alternatives.
- Predeclare the test: behavioral outcome, segment, time box, success and kill thresholds, and guardrails before observing results; prefer commitments over compliments (demand tests).
- Close the phase with its verdict: apply its checks and brief, scaled to the change:
| Phase | Verdict |
|---|---|
| Discover: problem, demand, or wedge unproven | BUILD, TEST FIRST, PARK, or STOP |
| Specify: validated intent needs a PRD | Requirements with acceptance scenarios and open decisions |
| Launch: built capability needs an audience | LAUNCH, LIMIT EXPOSURE, or HOLD |
| Learn: an experiment or launch has results | CONTINUE, ITERATE, PIVOT, STOP, or EXTEND TEST |
Gotchas
- Ground every claim in evidence: never invent quotes, metrics, demand, customer research, availability, or support capacity; effort, code volume, merges, stars, and traffic do not prove customer value.
- Gate external effects on authorization: drafts and local artifacts are reviewable work. Customer contact, CRM changes, publication, advertising, and spend require authorization for those effects; a launch plan authorizes none of them.
- Require readiness before customer exposure: a customer-facing rollout needs a current production-readiness result, with its blockers carried forward.
- Judge against the predeclared design: keep the original hypothesis, baseline, denominators, segment, and thresholds; explain deviations after observing results instead of moving the goalposts.
- Never omit unresolved risk: compact changes get compact briefs, but trust boundaries, edge cases, and open risks always stay visible.
What ships with it
2 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.
- 9d ago First seen · 43 lines · 20 tokens per session scan A f939ad785fc0
product-management is a skill published in the GitHub repository fmind/dot (11 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 873 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 2026-10-08.
Other skills, from other repositories
github-issues
Manage GitHub issues with gh: confirm repo and state, deduplicate, preserve evidence, and verify authorized creation, edits, labels, comments, or closure.
product-loop
Discovery, specification, launch, and learning for a product in one loop. Build-or-stop calls, MVP wedges, demand tests, customer interviews, PRDs, requirements, user journeys, acceptance, positioning, onboarding, rollout, pricing, pivots.
project-backlog
Turn audit findings into deduplicated, prioritized issue drafts with dependencies and explicit authorization before GitHub mutation.
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
work-on
End-to-end workflow for shipping a GitHub issue. Assesses complexity, builds a tailored workflow, and orchestrates skills from research through PR.