Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/oaustegard/claude-skills/challenging)<a href="https://agentmods.dev/skills/oaustegard/claude-skills/challenging"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/challenging/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/oaustegard/claude-skills/challenging"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/challenging.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 | $0.00061 | $0.03134 |
| Opus 5 | $0.00030 | $0.01567 |
| Sonnet 5 | $0.00012 | $0.00627 |
| Haiku 4.5 | $0.00006 | $0.00313 |
Grade A, and why
challenging 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 7d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Challenging — Adversarial Review
Adversarial review before shipping. Three paths, each with distinct trade-offs:
- Subagent path (Claude Code, primary). Native sub-Claude via the Task tool — zero API keys, fresh context window, same model. Best when available.
- External API path (claude.ai, Codex, headless). Gemini (cross-model + cross-context) or Anthropic API (cross-context). Costs an incremental API call but gives genuine outside perspective.
- Self path (any environment). The caller assistant inhabits the adversary persona in a dedicated response. Zero cost, retains full subject-matter context from the conversation. Weaker at catching same-session confabulations than fresh-context adversaries, stronger at catching local-convention and factual errors the artifact glosses over. Not a strict downgrade — a different failure-mode profile.
The adversary='auto' resolution (default) picks gemini → claude → self based on available credentials. Callers in Claude Code still use prepare() + Task tool explicitly (subagent is strictly better than self in that environment, and auto-detection of Claude Code is brittle).
Inspired by VDD (dollspace.gay) and Grainulation's anti-rationalization patterns. The drill helper adopts the 5 Whys pattern from Tim Kellogg's open-strix writeup. The self-path persona-inhabitation move is kin to generative-thinking's inversion — commit to the mode before evaluating.
Profiles
Pick the profile matching your artifact. Read only the profile you need — each is self-contained with persona, anti-rationalization table, evaluation criteria, and adversary system prompt.
| Profile | Use For | Iteration strategy | File |
|---|---|---|---|
prose |
Blog posts, essays, articles — generic prose competence | parallel replay | references/prose.md |
prose-register |
Prose with a named voice signature — fidelity check | parallel replay | references/prose-register.md |
analysis |
Research briefs, comparisons, synthesis | parallel replay | references/analysis.md |
code |
Scripts, implementations, PRs | parallel replay | references/code.md |
recommendation |
Technical decisions, architecture choices | parallel replay | references/recommendation.md |
philosophers |
Arguments, position pieces, design rationales — conceptual-layer audit | parallel replay | references/philosophers.md |
drill |
5 Whys on one finding from a review | sequential deepen | references/drill.md |
What ships with it
10 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.
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.
- 7d ago Changed 8a7d56e03e10
- 11d ago First seen · 221 lines · 61 tokens per session scan A 97bac851b910
challenging is a skill published in the GitHub repository oaustegard/claude-skills (148 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 3,134 once invoked, about $0.0003 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 skills, from other repositories
superdesign
Design or redesign frontend UI, presentations, and graphics on the Superdesign canvas with a choice of leading AI models. Use whenever the user wants to design a page, feature, flow, slide deck, or brand-new product; improve or reproduce existing UI; compare design results across top models; explore visual variants…
high-quality-slides
A method for creating polished presentation slides, including HTML slide decks, with research, a clear story, chosen visuals, and fixed layouts.
sora2
An Sora2 content-creation and work-analysis tool for finding works, users, comments, remixes, downloads, and media information, as well as uploading images and creating videos. Sora2 is a video-generation service.
remotion-performance-optimizer
Analyzes Remotion compositions for performance issues and provides optimization recommendations. Identifies expensive computations, unnecessary re-renders, large assets, memoization opportunities, and architecture improvements. Use when optimizing render times or when asked to "improve performance", "speed up…
remotion-asset-coordinator
Bridges asset requirements from motion design specs to production-ready assets. Parses specs for required assets, recommends free/paid sources, provides format conversion guidance, generates validated import code, and offers asset preparation checklists. Use when preparing assets for Remotion projects or when asked…
remotion-composition
Generates Remotion composition structure focusing ONLY on Sequence ordering, scene transitions, and duration mapping. Input is scene list with durations. Output is COMPOSITIONSTRUCTURE.md with Sequence layout and timing calculations. Use when organizing scenes or when asked to "structure composition", "layout scenes"…