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 BrennanJCollins/UnabatedPM-coaching --skill adversarial-stakeholder-prepgit clone --depth 1 https://github.com/BrennanJCollins/UnabatedPM-coachingWrote 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/brennanjcollins/unabatedpm-coaching/adversarial-stakeholder-prep)<a href="https://agentmods.dev/skills/brennanjcollins/unabatedpm-coaching/adversarial-stakeholder-prep"><img src="https://agentmods.dev/badge/skills/brennanjcollins/unabatedpm-coaching/adversarial-stakeholder-prep/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/brennanjcollins/unabatedpm-coaching/adversarial-stakeholder-prep"><img src="https://agentmods.dev/badge/skills/brennanjcollins/unabatedpm-coaching/adversarial-stakeholder-prep.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 | $0.00101 | $0.06228 |
| Opus 5 | $0.00051 | $0.03114 |
| Sonnet 5 | $0.00020 | $0.01246 |
| Haiku 4.5 | $0.00010 | $0.00623 |
Grade A, and why
Adversarial Stakeholder Prep 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 11d 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 — 467 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating Modes
This skill operates in two modes:
Conversation mode (default): Coach the PM through their stakeholder map, archetype each person, run the Adversarial Stakeholder Prompt for each one, and rewrite the opening based on what came back. Triggered by direct invocation or natural conversation.
Evaluate mode: Read a written pitch, proposal, roadmap doc, or meeting prep doc silently. Score whether the PM has accounted for the hidden incentive system in the room. Return structured findings. No conversation, no questions — just assessment. Triggered by the /audit orchestrator.
Evaluate Mode Instructions
When invoked in evaluate mode, you receive a written pitch, proposal, roadmap one-pager, or pre-meeting prep doc. Do NOT coach. Do NOT ask questions. Read and score whether the PM has decoded the room.
Score each dimension 1-5:
- 1 = Not present or fundamentally broken (no stakeholder thinking, just logic and features)
- 2 = Stakeholders named but only stated priorities surfaced (OKRs and titles)
- 3 = Some incentive thinking, but archetypes unclear and survival metrics vague
- 4 = Strong archetype reads with specific career concerns, openings tailored per stakeholder
- 5 = Exemplary — incentive map is explicit, archetypes are named, openings reduce risk / create credit / preserve turf for the right person
Dimensions to evaluate:
-
Stakeholder alignment — Does the document show evidence that the PM has decoded what each key stakeholder is actually optimizing for, beyond the stated OKR? Are stakeholders archetyped (Risk Shield / Credit Catcher / Tribal Guardian) and is the read specific enough to act on? Do the openings, framing, and tradeoff language address the survival metric, not the public agenda?
-
Messaging & communication — Is the message to each stakeholder tailored to their archetype? Does the document show that the PM has rehearsed objections from the stakeholder's vantage point, not the PM's own? Does it address objection #3 (the one they'd never say out loud), or only the polite objection on the surface?
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.
- 11d ago First seen · 467 lines · 101 tokens per session scan A bd0e3b30eca9
Adversarial Stakeholder Prep is a skill published in the GitHub repository BrennanJCollins/UnabatedPM-coaching (4 stars, last pushed 21d ago), licensed MIT. It adds 101 tokens to every session and 6,228 once invoked, about $0.0005 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
pm-brainstorm
A guided brainstorming workflow for exploring a new product idea before detailed research or requirements work. It collects basic information about the product, users, and problem through staged questions.
start-super-pm
Use when starting any product management task - automatically detects task type and invokes appropriate PM skill using intelligent routing.
pm-priority
A Chinese-language procedure for ranking several product requests when time or resources are limited. It supports scoring or grouping methods such as RICE, KANO, and MoSCoW to decide what should be done first.
pm-change
A requirements-change workflow for recording a proposed change, assessing its effects, and deciding whether to approve it.
pm-cross
A Chinese-language planning workflow for coordinating work between departments such as product, engineering, design, testing, operations, and legal.
pm-risk
A structured process for identifying, rating, responding to, and monitoring project risks before important delivery points or launch.