devils-advocate

An adversarial review of a code change, design, plan, or assumption. It deliberately looks for realistic ways the proposal could fail before release or a major decision.

In plain words
What is it for?
It is for stress-testing pull requests, designs, release plans, and technical assumptions, including the impact and mitigation for each identified risk.
Why use it?
It helps expose overlooked failure modes while there is still time to fix them. It reports only risks supported by concrete evidence and does not object merely for the sake of opposition.

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

Made for: Claude Code, Codex.

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 312 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 $0.00029 $0.00312
Opus 5 $0.00015 $0.00156
Sonnet 5 $0.00006 $0.00062
Haiku 4.5 $0.00003 $0.00031

Measured 2d ago against content hash b2c21e3751e7, 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.

plugins/flow/skills/devils-advocate/SKILL.md · 60 lines

What it actually says

Devil's Advocate

Stress-test failure modes so concrete risks are visible before they become problems. Use directly or as an adversarial review subagent.

Workflow

  1. Load the adversarial persona and failure-mode checklist below.
  2. Inspect the actual change or proposal and exercise every relevant checklist question.
  3. Report calibrated findings and acknowledge verified strengths.

Guardrails

Follow the persona boundaries. Do not oppose a sound approach merely to be contrarian, and do not inflate speculative concerns.

Output

For each finding, state severity, the specific failure mode, its evidence and impact, and the recommended mitigation. A substantiated clean bill of health is valid output.

Validation

Confirm each finding cites concrete code or design evidence and that severity is calibrated.

Example

Flag an unbounded upstream call as a cascading timeout risk and identify the timeout/error-path test that would mitigate it.

References

Files

What ships with it

3 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.

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 · 60 lines · 29 tokens per session scan A b2c21e3751e7

Subscribe to this mod's changes

devils-advocate is a skill published in the GitHub repository cofin/flow (15 stars, last pushed 3d ago), licensed Apache-2.0. It adds 29 tokens to every session and 312 once invoked, about $0.0001 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

write-documentation

Use when writing or substantially rewriting human-facing prose: documentation, README, guides, blog posts, emails, Slack messages, PR descriptions, release notes, or any text a human will read. Not for code comments, commit messages, or agent-to-agent communication.

DollarDill/beads-superpowers · 56 tokens

document-release

Use when implementation on a branch is complete and it is about to be merged or PR'd — or when finishing-a-development-branch reaches its docs-audit gate — and after code changes are committed, to ensure all project documentation accurately reflects shipped code. Covers README, ARCHITECTURE, CONTRIBUTING, CHANGELOG…

DollarDill/beads-superpowers · 103 tokens

stress-test

Use when a design, plan, or decision needs adversarial scrutiny before proceeding. Interrogates every branch of the decision tree, providing recommended answers and forcing explicit agreement or pushback. Triggers on "grill me", "stress test this", "poke holes", "challenge this design", or when…

DollarDill/beads-superpowers · 72 tokens

systematic-debugging

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

DollarDill/beads-superpowers · 21 tokens

writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code.

DollarDill/beads-superpowers · 21 tokens

dispatching-parallel-agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.

DollarDill/beads-superpowers · 26 tokens