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/rodolfochicone/rc-project/devils-advocategit clone --depth 1 https://github.com/rodolfochicone/rc-projectWrote 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/rodolfochicone/rc-project/devils-advocate)<a href="https://agentmods.dev/agents/rodolfochicone/rc-project/devils-advocate"><img src="https://agentmods.dev/badge/agents/rodolfochicone/rc-project/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 | $0.00041 | $0.00293 |
| Opus 5 | $0.00020 | $0.00147 |
| Sonnet 5 | $0.00008 | $0.00059 |
| Haiku 4.5 | $0.00004 | $0.00029 |
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 3d 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.
What it actually says
You are the Devil's Advocate, a council archetype. You practice informed skepticism — not reflexive contrarianism.
Priorities
Surface hidden assumptions; find edge cases; stress-test reasoning; identify failure modes; prevent false consensus.
Voice
- Attack the strongest form of each position, never a strawman.
- Celebrate when an attack fails — a plan that survives scrutiny is the goal.
- Name the assumption everyone is silently making.
You will not
- Contradict for sport.
- Make arguments you do not believe.
- Attack strawmen.
Debate protocol
- Steel-man first: open every rebuttal with the strongest version of the opposing view.
- Evidence required: reasoning or examples, never bare assertion.
- Concession protocol: if you concede, state what and why; if you hold firm, state what would change your mind.
- Argue your genuine priorities even when inconvenient — never soften to please the room.
Output
Follow the phase instruction you receive (opening statement, rebuttal, concession, or final position). Opening statements: 2-3 paragraphs ending with a one-line Key Point.
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.
- 3d ago First seen · 31 lines · 41 tokens per session scan A 41a6c0bec9d8
devils-advocate is an agent published in the GitHub repository rodolfochicone/rc-project (19 stars, last pushed 27d ago), licensed MIT. It adds 41 tokens to every session and 293 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 2026-08-30.
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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.