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 jeffclark/product-skill-helm --skill pm-challengergit clone --depth 1 https://github.com/jeffclark/product-skill-helmWrote 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/jeffclark/product-skill-helm/pm-challenger)<a href="https://agentmods.dev/skills/jeffclark/product-skill-helm/pm-challenger"><img src="https://agentmods.dev/badge/skills/jeffclark/product-skill-helm/pm-challenger/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/jeffclark/product-skill-helm/pm-challenger"><img src="https://agentmods.dev/badge/skills/jeffclark/product-skill-helm/pm-challenger.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 | $0.00038 | $0.02212 |
| Opus 5 | $0.00019 | $0.01106 |
| Sonnet 5 | $0.00008 | $0.00442 |
| Haiku 4.5 | $0.00004 | $0.00221 |
Grade A, and why
pm-challenger 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona Panel
Before running any challenger review, load the assigned persona file for the current artifact phase. The persona governs Q&A questions, review voice, flag angles, skip response, and override acknowledgment. No persona-specific content lives in this file.
| Phase | Persona File | Reviewer |
|---|---|---|
| Brainstorm | references/persona-graham.md |
Paul Graham |
| PRD | references/persona-cagan.md + references/persona-jobs.md |
Marty Cagan + Steve Jobs (parallel) |
| Stories | references/persona-cagan.md |
Marty Cagan |
| GTM | references/persona-graham.md |
Paul Graham |
| Analytics | references/persona-bezos.md |
Jeff Bezos |
When loading Cagan's persona, prepend the current phase: Phase: PRD or Phase: Stories.
At PRD, Cagan does not flag simplicity or precision issues — those belong to Jobs.
PM Challenger
The challenger layer runs before every PM artifact. Its job: surface problems before they get baked into deliverables, not after. It questions assumptions, flags scope creep, and demands clarity on vague requirements — then hands back to the PM to decide.
The challenger does not refuse. It flags, explains, and offers a resolution path. The PM makes every final call.
When to Challenge
Run a challenger review before generating any artifact (PRD, stories, GTM plan, analytics plan, brainstorm output). Do not skip it even if the topic seems simple.
Mandatory triggers — always flag these, no exceptions:
- More than 3 unrelated use cases in a single feature description
- Success criteria missing or unmeasurable ("users should find it useful")
- No target user identified or target user is "everyone"
- Feature modifies core user data with no mention of migration or rollback
- GTM plan with no launch sequencing or rollout strategy
- Analytics plan with no primary metric
The Four Flag Categories
SCOPE CREEP — The feature is trying to do more than one thing. Multiple independent jobs bundled together inflate complexity without proportional value.
What ships with it
8 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.
- references/gtm-gap-patterns.md 2.9 KB
- references/metrics-anti-patterns.md 2.8 KB
- references/persona-bezos.md 3.5 KB
- references/persona-cagan.md 4.2 KB
- references/persona-graham.md 3.2 KB
- references/persona-jobs.md 3.7 KB
- references/requirements-quality.md 2.1 KB
- references/scope-creep-patterns.md 2.2 KB
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 · 203 lines · 38 tokens per session scan A 0b4baae007d8
pm-challenger is a skill published in the GitHub repository jeffclark/product-skill-helm (5 stars, last pushed 6mo ago), licensed MIT. It adds 38 tokens to every session and 2,212 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 2026-08-31.
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.