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 perniemann/pnCore --skill pn-skeptic-challengegit clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/perniemann/pncore/pn-skeptic-challenge)<a href="https://agentmods.dev/skills/perniemann/pncore/pn-skeptic-challenge"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-skeptic-challenge/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/perniemann/pncore/pn-skeptic-challenge"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-skeptic-challenge.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 | $0.00043 | $0.02042 |
| Opus 5.5 | $0.00017 | $0.00817 |
| Sonnet 5.5 | $0.00009 | $0.00408 |
| Haiku 4.5 | $0.00004 | $0.00204 |
Grade A, and why
pn-skeptic-challenge 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 1mo 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skeptic challenge
When to use
- After pn-writing-plans, before running specialists (orchestrator and pn-build).
- After implementation (pn-design, optional reviewer pass): challenge the built output—see "Skeptic on output (post-build)" below.
Mission
Challenge the plan and chosen approach. Ask: Is this the best way? What alternatives exist? Are we over-engineering or missing a simpler path? Do not rubber-stamp; output either "proceed as planned" with brief rationale or "revise plan: [concrete changes]" and gate on user/orchestrator confirmation before specialists run.
Industry and best practices research
Before questioning the plan or output, research the current state of industry standards and best practices for the stack and domain:
- Identify the domain: Extract stack, framework, and domain from the plan or discovery spec (e.g. React 19, Next.js 15, Node API, auth, payments, a11y).
- Research: Use web search to find the most recent industry standards, recommendations, and best practices. Target official docs, OWASP, W3C, framework changelogs, and respected community guides.
- Compare: Evaluate the plan or output against findings. Note: Does it follow current patterns? Are there newer APIs or deprecated approaches? Are security or a11y best practices met?
- Goodhart check: When the plan or output cites a numeric goal (LCP, INP, lighthouse, coverage %, token budget), confirm the metric is being used as feedback rather than target. If it is a target, name what underlying property it is meant to proxy and check whether optimizing the metric would actually move the property — not just the score.
- Surface gaps: In the skeptic verdict, include a brief "Industry alignment" note: alignments and any gaps or recommendations from the research.
Instructions
- Research industry and best practices (see section above). Then question the plan: Review the implementation plan (and discovery spec when available). Identify the core approach, assumptions, and order of work.
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.
- 1mo ago First seen · 92 lines · 43 tokens per session scan A e4650b9b5af1
pn-skeptic-challenge is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed 6d ago), licensed MIT. It adds 43 tokens to every session and 2,042 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
otto-review-remediation
Handle trusted reviewers' change requests on Otto PRs.
feature-publish
Commit the feature, write the PR body, publish in the selected mode, and drive the PR.
cocoreview
CocoReview — structured code review with six-severity findings vocabulary, progressive disclosure architecture, and universal anti-pattern baseline. Invoked via $review [file] [--complexity] [--security] [--architecture] [--language ].
understand-pr
Review a PR the way a seasoned maintainer would — build an independent model before seeing the diff, investigate the implementation and history, verify material claims, and return a concise briefing. Use for any PR review, self-review, or re-review.
performance-review
Performance-focused code review for identifying bottlenecks and optimization opportunities.
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.