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.
git clone --depth 1 https://github.com/product-on-purpose/pm-skillsWrote 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/commands/product-on-purpose/pm-skills/chain)<a href="https://agentmods.dev/commands/product-on-purpose/pm-skills/chain"><img src="https://agentmods.dev/badge/commands/product-on-purpose/pm-skills/chain/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/commands/product-on-purpose/pm-skills/chain"><img src="https://agentmods.dev/badge/commands/product-on-purpose/pm-skills/chain.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 | $0.00028 | $0.00495 |
| Opus 5 | $0.00014 | $0.00247 |
| Sonnet 5 | $0.00006 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
chain 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 — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run an ad-hoc chain of pm-skills in the order given, passing the shared context to every step.
Parse the input
$ARGUMENTS carries a chain expression followed by free-form context.
- Extract flags first, wherever they appear:
--auto,--force-auto,--dry-run,--thread. - The chain expression is exactly the leading separator-joined list of skill names (
,and->equivalent; mixing allowed). It ends after the first name that is NOT followed by a separator; everything after that is the context, even when the context words look like skill names. A trailing separator with nothing after it is an error to surface, not to guess around. - Everything after the chain expression is the context. This command parses the BOUNDARY only; all skill-name validation belongs to the engine.
Examples: /chain define-problem-statement -> define-hypothesis --thread Mobile checkout drop-off runs two steps with --thread, context "Mobile checkout drop-off". Lowercase context is fine: /chain deliver-prd, deliver-user-stories mobile checkout redesign is two steps with context "mobile checkout redesign" (the boundary is the missing separator after deliver-user-stories, not the letter case).
Confirm and dispatch
- Restate in one line: the parsed steps in order, the flags, and the context.
- Invoke the
utility-pm-workflow-orchestratorskill fromskills/utility-pm-workflow-orchestrator/SKILL.mdwith that chain, context, and flags (a Mode B run). The engine validates every name pre-flight and owns all run rules; this command adds none. The grammar lives inskills/utility-pm-workflow-orchestrator/references/PARSE-CONTRACT.md(Mode B Chain Expression Contract). - Relay the engine's per-step blocks and terminal output, including the promotion suggestion for reusable chains.
Nothing is persisted beyond the engine's own gitignored run artifacts. To make a chain durable, follow the completion suggestion to utility-pm-workflow-builder. While the native engine path is EXPERIMENTAL, recommend --dry-run first.
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 · 26 lines · 28 tokens per session scan A 92545bbc4c2b
chain is a command published in the GitHub repository product-on-purpose/pm-skills (652 stars, last pushed yesterday), licensed Apache-2.0. It adds 28 tokens to every session and 495 once invoked, about $0.0001 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 commands, from other repositories
discover
Structured product discovery from problem to validated experiments.
okr-planning
Structured OKR creation aligned with company objectives.
write-stories
Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria.
plan-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.
epic-dev
Epic/sprint development workflow with git worktrees, GitHub issues, and phased delivery.
triage
Triages an unprioritized list of bugs, debt, and tasks into a full MoSCoW breakdown with justification and an attack order.