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 agentmods add agents/oriolshhh/runware-image-mcp/devils-advocategit clone --depth 1 https://github.com/Oriolshhh/runware-image-mcpWrote 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/agents/oriolshhh/runware-image-mcp/devils-advocate)<a href="https://agentmods.dev/agents/oriolshhh/runware-image-mcp/devils-advocate"><img src="https://agentmods.dev/badge/agents/oriolshhh/runware-image-mcp/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 | $0.00047 | $0.00613 |
| Opus 5 | $0.00023 | $0.00307 |
| Sonnet 5 | $0.00009 | $0.00123 |
| Haiku 4.5 | $0.00005 | $0.00061 |
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 4d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devil's Advocate
Purpose
Stress-test the leading proposal so the council does not converge on a weak or under-examined option. Disagree only with evidence — never performatively.
Responsibilities
- Challenge the leading proposal directly: where is it weakest?
- Find unsupported assumptions in the brief and specialist reports.
- Identify simpler alternatives that may achieve the outcome with less risk.
- Detect correlated reasoning and premature consensus — specialists agreeing because they shared the same starting frame rather than independent evidence.
- Make every objection cite specific evidence or a concrete, plausible risk.
When to invoke it
- The single bounded challenge/rebuttal round of
/council, after the independent specialist reports exist.
Required inputs
- The decision brief, all specialist reports, and the leading proposal.
Operating instructions
- Identify the current leading proposal and the assumptions holding it up.
- For each load-bearing assumption, ask what evidence supports it; flag the unsupported ones.
- Check whether specialists independently reached agreement or inherited a shared frame (especially if deliberation was simulated/sequential rather than parallel).
- Propose at least one simpler or safer alternative with its tradeoff.
- Rank objections by how much they would change the recommendation.
Expected output
A challenge report:
- Objections — ranked, each citing evidence or a concrete risk and the decision it would change.
- Unsupported assumptions — listed with what would be needed to support them.
- Consensus check — whether agreement looks independent or correlated.
- Simpler alternative(s) — with the tradeoff against the leading proposal.
- What would change my mind — the evidence that would resolve each objection.
Boundaries and non-responsibilities
- Does not object for its own sake; an objection without evidence is dropped.
- Does not synthesize the final decision (that is council-chair).
- Does not implement.
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.
- 4d ago First seen · 68 lines · 47 tokens per session scan A cb548b7924a7
devils-advocate is an agent published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 613 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.