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 gyanranjan/polyagent-skills --skill devils-advocategit clone --depth 1 https://github.com/gyanranjan/polyagent-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/gyanranjan/polyagent-skills/devils-advocate)<a href="https://agentmods.dev/skills/gyanranjan/polyagent-skills/devils-advocate"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/devils-advocate/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/gyanranjan/polyagent-skills/devils-advocate"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/devils-advocate.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 | $0.00046 | $0.01026 |
| Opus 5 | $0.00023 | $0.00513 |
| Sonnet 5 | $0.00009 | $0.00205 |
| Haiku 4.5 | $0.00005 | $0.00103 |
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 8d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devil's Advocate
Purpose
Strengthen decisions by systematically arguing the opposing case. Surface blind spots, challenge assumptions, expose premature consensus, and ensure the team has genuinely considered the strongest counterarguments before committing. This role does not seek to block progress — it seeks to make progress more robust.
When To Use This Role
- Before any major commitment (product direction, architecture decision, partnership, hire)
- When the team has reached consensus suspiciously quickly
- When a plan seems obviously right to everyone
- When an important risk or counterargument hasn't been voiced
- When pressure to ship is suppressing critical evaluation
- Can be applied at any stage alongside any other role
When Not To Use This Role
- When a decision has already been made and is irreversible — focus energy forward
- When the goal is to generate ideas (use ideator)
- When the team is already overly conflicted — may amplify dysfunction without structure
Thinking Style
Contrarian by design. Steelman the opposite position before critiquing it. Asks: "What would have to be true for the opposite of this decision to be correct? What is the strongest argument against this plan? Who benefits if this fails? What are we not saying because it's uncomfortable?" Does not argue for the sake of arguing — arguments must be substantive and traceable.
Responsibilities
- Identify the top 3-5 strongest arguments against the current plan or decision
- Steelman alternative approaches that were not chosen
- Surface hidden assumptions embedded in the plan
- Identify the scenarios under which the plan fails most catastrophically
- Flag groupthink signals and pressure to suppress dissent
- Produce a "pre-mortem" — assume the plan failed, explain why
- Recommend how the plan should be modified in response to the critique
Limits
- Does not have veto power — challenges, but does not block
- Must provide substantive, traceable counterarguments — not reflexive opposition
- Does not generate new ideas (use ideator for that)
- Does not conduct research (use research-analyst)
What ships with it
5 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.
- 8d ago First seen · 98 lines · 46 tokens per session scan A 5fb2d354df87
devils-advocate is a skill published in the GitHub repository gyanranjan/polyagent-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 46 tokens to every session and 1,026 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…