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 ljucask/pureinn-product-development --skill pm-stress-testgit clone --depth 1 https://github.com/ljucask/pureinn-product-developmentWrote 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/ljucask/pureinn-product-development/pm-stress-test)<a href="https://agentmods.dev/skills/ljucask/pureinn-product-development/pm-stress-test"><img src="https://agentmods.dev/badge/skills/ljucask/pureinn-product-development/pm-stress-test/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/ljucask/pureinn-product-development/pm-stress-test"><img src="https://agentmods.dev/badge/skills/ljucask/pureinn-product-development/pm-stress-test.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 | $0.00000 | $0.05240 |
| Opus 5 | $0.00000 | $0.02620 |
| Sonnet 5 | $0.00000 | $0.01048 |
| Haiku 4.5 | $0.00000 | $0.00524 |
Grade A, and why
pm-stress-test 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PM - Stress Test (stakeholder pushback simulator)
Agent mode (--agent)
This skill's value is the live dialogue - --agent is not supported. If invoked with --agent, warn once ("this skill needs interactive back-and-forth; agent mode would hollow it out") and proceed interactively.
What this skill does
Plays a specific skeptical stakeholder and stress-tests your proposal before the real room does. You bring the thing to be challenged; the skill attacks it from that stakeholder's actual point of view, in multiple rounds, and hands you a prep summary.
The core value is the quality of the questions. A generic "what's your ROI?" teaches you nothing. The right persona + the right pressure on the right weak spot is what prepares you for the room. This skill is built on a distilled bank of real objections, question types, stakeholder profiles, adversarial methods, and failure patterns.
Cross-phase. Run it whenever you are about to be challenged: an exec/product-council review, an investor pitch, a board meeting, a budget defense, a security/legal review, or any contentious internal push.
Two modes:
| Mode | When | What it does |
|---|---|---|
| Live pushback (default) | You want to rehearse | Iterative back-and-forth: persona fires questions, you answer, it presses harder. Ends with a prep summary. |
| Written gauntlet | You want a checklist, no dialogue | Produces the full calibrated question set + weakness diagnosis + prep summary in one pass, no live rounds. |
What the skill is NOT: it is not a yes-man and not a cheerleader. It is also not a fact generator - it challenges what is in your proposal, it does not invent facts about your business (see the hard rule below).
Hard rule: sharp, not fabricated
The adversary is only useful if it is honest. So:
- Challenge what is in the proposal. Never invent facts about the user's business, numbers, or market and then attack the invention. Attack the gap, the assumption, the thing that is missing or thin.
- A real skeptic makes assumptions out loud and probes them - that is fair game ("you are assuming X; what if not?"). Asserting a false fact as if it were the user's is not.
- If the proposal is too thin to challenge on a given dimension, that IS the finding: name the gap and ask the question that exposes it. Do not fill the void with invented detail to have something to attack.
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 · 283 lines · 0 tokens per session scan A 33d934aa7a74
pm-stress-test is a skill published in the GitHub repository ljucask/pureinn-product-development (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,240 tokens. 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
ai-native-design
A workflow for turning a product brief and API contract into frontend design prompts and implementation guidance. It supports three outside design channels and keeps generated frontend work aligned with the same brief and contract.
backend-development
A set of instructions for building server-side code such as APIs and database-backed applications. It uses API contracts, data models, the chosen technology stack, and tests as the project’s reference points.
decision-gate
A decision checkpoint for software-project workflows. After each phase produces its files, it asks the user to accept the result, request a change, add information, or regenerate it before the next phase begins.
frontend-development
A set of instructions for building the user-facing part of a web application, such as its pages, controls, and interactions. It applies to single-page applications and follows the project’s API, product, technology, and design documents.
relay
A Chinese-language procedure for handing an unfinished task from one AI session to another without losing its context.
validation-loop
A development routine that checks each important file immediately after it is changed by running the project’s build, lint, type-check, or test commands.