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 t0ddharris/claude-code-skills --skill devils-advocategit clone --depth 1 https://github.com/t0ddharris/claude-code-skillsWrote 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/t0ddharris/claude-code-skills/devils-advocate)<a href="https://agentmods.dev/skills/t0ddharris/claude-code-skills/devils-advocate"><img src="https://agentmods.dev/badge/skills/t0ddharris/claude-code-skills/devils-advocate.svg" alt="Measured on agentmods" 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 | $0.00164 | $0.02370 |
| Opus 5 | $0.00082 | $0.01185 |
| Sonnet 5 | $0.00033 | $0.00474 |
| Haiku 4.5 | $0.00016 | $0.00237 |
Grade A, and why
devils-advocate 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 6d 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.
Devil's Advocate
Get a critique from an outside model (Google Gemini 3.1 Pro by default) to pressure-test work before it ships. The whole reason this skill exists is that Claude and the user may share the same blind spots after working on a piece of content together. Sending the work to a model in a different lineage surfaces weaknesses that neither of you will catch alone.
Never substitute your own critique for this tool. If you find yourself about to write "here's what I think the weak points are" without running the script, stop — you are defeating the entire purpose of the skill.
When to use this skill
Use it when the user explicitly asks for a second opinion, a devil's advocate read, or to poke holes in something. Also proactively suggest it when:
- The user is about to ship high-stakes work (a public launch plan, executive-level messaging, a pricing decision, a bet-the-quarter initiative).
- You and the user have been iterating for a while and the work feels "done" — fresh eyes matter most when confirmation bias is strongest.
- The user is weighing a decision with several defensible answers (a strategy shift, a channel bet, an org change).
- A plan makes a claim that would be expensive to get wrong (projected revenue, headcount, conversion lift).
Do NOT reach for this skill for quick copy edits, tactical wordsmithing, or requests the user clearly wants done inside Claude. This is a heavier tool meant for moments where an outside critique has real value.
Prerequisites
GOOGLE_AI_STUDIO_API_KEYmust be available as an environment variable or in a.envfile at your project root.- The script uses only the Python standard library. No installs required.
If the key is missing, the script will exit with a clear error and a link to create one.
How to run it
The script lives at .claude/skills/devils-advocate/scripts/challenge.py (relative to your project root, once the skill is installed in .claude/skills/).
1. Critique files
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.
- 6d ago First seen · 203 lines · 164 tokens per session scan A c66ba4a49c04
devils-advocate is a skill published in the GitHub repository t0ddharris/claude-code-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 164 tokens to every session and 2,370 once invoked, about $0.0008 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
understand-diff
Use when you need to analyze git diffs or pull requests to understand what changed, affected components, and risks.
auto-test-code
A structured process for critically reviewing and testing software code. It records review findings, test plans, commands, results, and supporting files in a project workspace.
git-pr-review
A read-only reviewer for GitHub pull requests, which are proposed code changes submitted for review. It produces an evidence-based report about whether a pull request should be merged.
code-reviewer
Use when reviewing Spring Boot 4 / Java 17+ code with concrete files or diffs — pull requests, modules, or pasted Java/Spring sources — for migration risks, architecture boundary leaks, JSpecify null-safety gaps, security flaws, performance regressions, or Spring Data pitfalls. Not for Kotlin-only code, non-Spring…
review
Plan-aware graph-enhanced code review before merge. CRITICAL issues block merge. Use after fix/verify.
flutter-dart-code-review
Library-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns (BLoC, Riverpod, Provider, GetX, MobX, Signals), Dart idioms, performance, accessibility, security, and clean architecture.