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 skills/drn/dots/devils-advocatenpx skills add drn/dots --skill devils-advocategit clone --depth 1 https://github.com/drn/dotsWhat 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 | $0.00048 | $0.01116 |
| Opus 5 | $0.00024 | $0.00558 |
| Sonnet 5 | $0.00010 | $0.00223 |
| Haiku 4.5 | $0.00005 | $0.00112 |
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.
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:
- Is this actually true? What evidence supports it?
- Under what conditions does this break? Edge cases?
- 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?
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.
- 2d ago First seen · 149 lines · 48 tokens per session scan A 0e8c8553fa87
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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…
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.
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.