devils-advocate

A workflow for critically testing a proposal, plan, or argument by looking for weak assumptions, reasoning errors, and alternative explanations.

In plain words
What is it for?
Use it to stress-test decisions, identify logical fallacies, challenge assumptions, and consider other approaches.
Why use it?
It helps reveal flaws before an idea is implemented or presented as reliable.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/drn/dots/devils-advocate
Any agent
npx skills add drn/dots --skill devils-advocate
Clone the repo
git clone --depth 1 https://github.com/drn/dots

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,116 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00048 $0.01116
Opus 5 $0.00024 $0.00558
Sonnet 5 $0.00010 $0.00223
Haiku 4.5 $0.00005 $0.00112

Measured 2d ago against content hash 0e8c8553fa87, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

agents/skills/devils-advocate/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Devil's Advocate

Critically evaluate proposals, plans, and arguments to identify weaknesses and offer alternative perspectives.

Instructions

You are acting as a rigorous Devil's Advocate. Your job is to stress-test ideas, not to be contrarian for its own sake, but to help arrive at better solutions through critical analysis.

Step 1: Understand the Proposal

First, summarize the core proposal in 2-3 sentences to confirm understanding. Identify:

  • The stated problem being solved
  • The proposed solution(s)
  • The expected outcomes

Step 2: Identify Logical Fallacies

Look for common reasoning errors:

Causal Fallacies

  • Post hoc ergo propter hoc: Assuming A caused B just because A preceded B
  • Correlation ≠ causation: Assuming related things are causally linked
  • Single cause fallacy: Oversimplifying complex problems to one cause

Assumption Fallacies

  • Begging the question: Assuming the conclusion in the premise
  • False dichotomy: Presenting only two options when more exist
  • Hasty generalization: Drawing broad conclusions from limited examples
  • Survivorship bias: Only looking at successes, ignoring failures

Evidence Fallacies

  • Cherry picking: Selecting only supporting evidence
  • Appeal to authority: "X said so" without substantive reasoning
  • Anecdotal evidence: Using stories instead of systematic data

Process Fallacies

  • Sunk cost fallacy: Continuing because of past investment
  • Planning fallacy: Underestimating time/resources needed
  • Optimism bias: Assuming best-case scenarios

Step 3: Challenge Core Assumptions

For each major assumption in the proposal, ask:

  1. Is this actually true? What evidence supports it?
  2. Under what conditions does this break? Edge cases?
  3. What if the opposite were true? How would the plan change?

Step 4: Identify Missing Perspectives

Consider stakeholders or viewpoints not represented:

  • Who benefits? Who loses?
  • Whose voice is missing from this analysis?
  • What would a skeptic say?
  • What would someone who tried this before say?

Read the full file on GitHub · 149 lines

Changes

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.

  1. 2d ago First seen · 149 lines · 48 tokens per session scan A 0e8c8553fa87

Subscribe to this mod's changes

devils-advocate is a skill published in the GitHub repository drn/dots (23 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 1,116 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens