devil

devil is a skill for Claude Code, Codex from mishahanin/heading-os. It costs 127 tokens per session (2,925 once invoked), scanned A, original, Apache-2.0.

A critique skill that produces a requested number of arguments against a position or decision. Each point has a severity label such as blocker, high, medium, or low.

In plain words
What is it for?
Use it to challenge text, decisions, or the latest substantive position in a conversation.
Why use it?
It provides deliberate counterarguments that can expose weaknesses or risks in a plan or claim.

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/mishahanin/heading-os/devil
Any agent
npx skills add mishahanin/heading-os --skill devil
Clone the repo
git clone --depth 1 https://github.com/mishahanin/heading-os

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for devil

README.md
[![agentmods](https://agentmods.dev/badge/skills/mishahanin/heading-os/devil.svg)](https://agentmods.dev/skills/mishahanin/heading-os/devil)
Your own site
<a href="https://agentmods.dev/skills/mishahanin/heading-os/devil"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/devil.svg" alt="Measured on agentmods" height="20"></a>
Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,925 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 $0.00127 $0.02925
Opus 5 $0.00063 $0.01463
Sonnet 5 $0.00025 $0.00585
Haiku 4.5 $0.00013 $0.00293

Measured 4d ago against content hash 606fe3a259a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devil 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 4d 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.

.claude/skills/devil/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/devil - Force N contrarian critique points

Manual sycophancy-breaker. When the user invokes /devil N they are explicitly summoning a contrarian critic. It produces exactly N severity-tagged adversarial points against a target position, from distinct angles, in committed prose. Cheap alternative to /council (external Gemini+Grok) and /scrutinize (multi-phase VIIA). Single-shot - after Phase 2 the skill exits and normal posture resumes.

Design spec: docs/superpowers/specs/2026-05-13-devil-skill-design.md (data overlay: .heading-os-data/docs/superpowers/specs/2026-05-13-devil-skill-design.md).

Phase 1 - Pre-flight + target identification

Three sub-steps, all silent on success.

Optional angle priming. Before you identify the target, you may consult the shared method catalog to widen the attack surface beyond the default angle pool. Draw from the risk, competitive, and framing families: python scripts/elicit.py list --category risk returns Pre-mortem Analysis, Failure Mode Analysis, and Assumption Audit. Use a method only to sharpen a real cut; never let it manufacture a point that violates the honesty floor. Skip this entirely when the angles are already obvious. Catalog: reference/elicitation-methods.md.

1.1 Parse N + detect inline form

Read $ARGUMENTS:

  • Empty -> N = 5, target = walk-back (1.3)

  • Token 1 is "1" through "10":

    • Only one token -> N = int(token1), target = walk-back
    • Followed by : -> N = int(token1), target = inline (everything after the :, stripped)
  • Token 1 is not an integer in 1-10 ("0", "100", "abc", "5.5", "-3") -> abort with the single-line error and stop:

    /devil expects N between 1 and 10. Got: {token1}. Try `/devil 5` or `/devil 5: <inline claim>`.
    

If the inline form is detected but the inline claim is empty (e.g., /devil 5: with nothing after the colon) -> abort with:

/devil 5: requires an inline claim after the colon, or use bare `/devil 5` to walk back to the latest claim in conversation.

Read the full file on GitHub · 267 lines

Files

What ships with it

1 file 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. 4d ago First seen · 267 lines · 127 tokens per session scan A 606fe3a259a4

Subscribe to this mod's changes

devil is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed today), licensed Apache-2.0. It adds 127 tokens to every session and 2,925 once invoked, about $0.0006 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

create-modal

Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.

marcus/sidecar · 69 tokens

merge-strategy

Git merge strategies, conflict resolution approaches, merge vs rebase recommendations, and branch integration patterns in sidecar. Covers pull strategy menu, direct merge workflow, squash merge, commit message templates, configurable defaults, and protected branches. Use when working on git merge features or making…

marcus/sidecar · 63 tokens

autoprompt

Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.

Spielewoy/autoprompt-skill · 56 tokens

autoprompt

Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.

Spielewoy/autoprompt-skill · 56 tokens

openlore-brainstorm

Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.

clay-good/OpenLore · 40 tokens

ap-juror

L4 terminal leaf - G7 SIGN-OFF. One independent sign-off panel seat that saw none of the intermediate work. Binary PASS/FAIL on opened evidence; default-FAIL. A FAIL naming a P0/P1 blocker is NOT arbitrable into PASS.

Spielewoy/autoprompt-skill · 58 tokens