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 mracal/vibe-engineering --skill devil-advocate-reviewgit clone --depth 1 https://github.com/mracal/vibe-engineeringWrote 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/mracal/vibe-engineering/devil-advocate-review)<a href="https://agentmods.dev/skills/mracal/vibe-engineering/devil-advocate-review"><img src="https://agentmods.dev/badge/skills/mracal/vibe-engineering/devil-advocate-review/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/mracal/vibe-engineering/devil-advocate-review"><img src="https://agentmods.dev/badge/skills/mracal/vibe-engineering/devil-advocate-review.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 | $0.00035 | $0.00520 |
| Opus 5 | $0.00017 | $0.00260 |
| Sonnet 5 | $0.00007 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
vibe-devil-advocate-review 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 10d 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.
This is a copy
100% identical to vibe-devil-advocate-review — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
vibe-devil-advocate-review
Before shipping a recommendation, challenge it. The goal is to find weaknesses BEFORE they become production incidents.
When to Use This Skill
- Before sending a design document for approval
- Before shipping a recommendation that combines multiple inputs
- Before merging a large feature branch
- When you feel "too confident" about a solution
- User asks for a review or second opinion
When NOT to Use This Skill
- Trivial changes (typo fixes, formatting)
- When the user explicitly says "just ship it"
- During brainstorming (don't kill ideas before they form)
- For code review of small PRs (use
vibe-quality-loopinstead)
The 5 Dimensions
Challenge the work across:
- Consistency — Do all parts agree with each other? Are there contradictions?
- Completeness — What's missing? What edge cases are unaddressed? What blind spots exist?
- Actionability — Is every recommendation concrete and measurable? Can someone actually do this?
- Alignment — Does this match the stated goals, constraints, and user needs?
- Risk — What could go wrong? What are the second-order effects? What's the blast radius of failure?
Steps
- Read the artifact thoroughly — don't skim
- For each dimension, actively try to find problems. Assume there ARE problems.
- Score each dimension 1-5 (1=critical issues, 5=solid)
- List specific issues with evidence
- Deliver verdict: APPROVE / REVISE (with required changes) / REJECT (with blocking issues)
Output Format
Devil's Advocate Review
| Dimension | Score | Issues Found |
|---|---|---|
| Consistency | X/5 | [count] |
| Completeness | X/5 | [count] |
| Actionability | X/5 | [count] |
| Alignment | X/5 | [count] |
| Risk | X/5 | [count] |
Critical Issues
- [Issue with evidence]
Warnings
- [Non-blocking concern]
Verdict: APPROVE / REVISE / REJECT
[Rationale]
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.
- 10d ago First seen · 64 lines · 35 tokens per session scan A a35fa3a07d68
vibe-devil-advocate-review is a skill published in the GitHub repository mracal/vibe-engineering (3 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 520 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to vibe-devil-advocate-review, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
code-intelligence-contract
Use when dependency, call-chain, blast-radius, architecture, domain-flow, or unfamiliar-codebase analysis needs an optional vendor-neutral code-intelligence provider.
lua-client-server-contract-audit
Use when normalized Lua client/server RPC contract copies or generated protocol tables disagree on opcode, request-response fields, types, ordering, or source authority.
mmorpg-packet-protocol-review
Use when a C++ server and Unity client protocol manifest or wire compatibility review covers packet version negotiation, numeric opcode registry, byte layout order, direction, and request-response pairing.
review-swarm
Use when reviewing a known change set through parallel read-only code, architecture, test, safety, or product lanes with disjoint concerns and one integrator verdict.
agent-code-review-swarm
Agent skill for code-review-swarm - invoke with $agent-code-review-swarm.
agent-swarm-pr
Agent skill for swarm-pr - invoke with $agent-swarm-pr.