contrarian

contrarian is a skill for Claude Code, Codex from adonai-labs/agent-runway. It costs 44 tokens per session (918 once invoked), scanned A, original, MIT.

An adversarial review of an important technical decision. It deliberately argues against the selected approach and considers alternatives, warning signs, and whether to proceed.

In plain words
What is it for?
Use it to challenge architecture or implementation choices, compare alternatives, identify failure signals, and reach a go, conditional-go, or stop decision.
Why use it?
It helps reveal blind spots and risks caused by commitment to a particular solution. This is useful before high-impact implementation begins.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to challenge architecture or implementation choices, compare alternatives, identify failure signals, and reach a go, conditional-go, or stop decision.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adonai-labs/agent-runway/contrarian
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.

Any agent
npx skills add adonai-labs/agent-runway --skill contrarian
Clone the repo
git clone --depth 1 https://github.com/adonai-labs/agent-runway

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 contrarian

README.md
[![agentmods](https://agentmods.dev/badge/skills/adonai-labs/agent-runway/contrarian/github.svg)](https://agentmods.dev/skills/adonai-labs/agent-runway/contrarian)
Your own site
<a href="https://agentmods.dev/skills/adonai-labs/agent-runway/contrarian"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/contrarian/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.

agentmods 80×15 button for contrarian

Your own site · 80×15
<a href="https://agentmods.dev/skills/adonai-labs/agent-runway/contrarian"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/contrarian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 918 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00044 $0.00918
Opus 5 $0.00022 $0.00459
Sonnet 5 $0.00009 $0.00184
Haiku 4.5 $0.00004 $0.00092

Measured 11d ago against content hash 1c0ae18fad5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

contrarian 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 11d 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.

src/core/skills/contrarian/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contrarian Review

Apply shared policy: ../shared/caveman-skill-engineering.md

Invoke Command

/contrarian
[paste /contrarian Handoff]

Complete the handoff template from .agent-runway/skills/lead/validation-templates.md and pass it as context.

Purpose

Challenge the chosen approach before high-impact implementation begins.

Your role is adversarial: find the strongest argument against the selected path. The implementation agent that invoked this skill has cognitive bias toward its chosen approach — your job is to surface what it cannot see.

Workflow

Step 1 — Confirm Understanding

Restate the chosen approach in one sentence. If the handoff is ambiguous, ask one clarifying question before proceeding.

Step 2 — Codebase Search

Search the codebase for evidence relevant to the chosen approach:

  • Existing patterns that conflict or align with it
  • Prior implementations of similar decisions and their outcomes
  • Architectural boundaries that the approach may violate
  • Shared infrastructure, contracts, or dependencies affected

Document every relevant file or pattern found.

Step 3 — Strongest Counter-Argument

Identify the most powerful argument against the chosen approach.

Requirements:

  • Must be grounded in codebase evidence or a concrete structural risk
  • Must be specific — not a generic concern like "this could be complex"
  • Must identify what specifically would break and under what condition

Step 4 — Viable Alternative

Identify at least one alternative not selected in the handoff.

Requirements:

  • Must be concrete and implementable given the stated constraints
  • Must describe the key trade-off vs. the chosen approach in one sentence
  • Do not simply repeat alternatives already rejected in the handoff — offer a fresh angle if possible

Step 5 — Invalidation Signals

List 2–4 specific conditions under which the chosen approach would fail or require significant rework. (Maps to the "Invalidation signals" field in the Phase 0 contrarian gate.)

Read the full file on GitHub · 129 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. 11d ago First seen · 129 lines · 44 tokens per session scan A 1c0ae18fad5f

Subscribe to this mod's changes

contrarian is a skill published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 21d ago), licensed MIT. It adds 44 tokens to every session and 918 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.

Related

Other skills, from other repositories

sdd-tasks

Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.

Gentleman-Programming/gentle-ai · 25 tokens

pr-blocker-summarizer

Summarizes open pull requests into a blockers-first standup digest. Activates when the user asks to summarize open PRs, find blocked pull requests, generate a PR standup, or triage review backlog from a PR export.

FrancyJGLisboa/agent-skill-creator · 54 tokens

review-work

Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.

code-yeongyu/oh-my-openagent · 63 tokens

ponytail-lazy-senior-dev

Applies the "lazy senior developer" mindset. Use this skill whenever generating, modifying, reviewing code, or fixing bugs to prioritize code reuse, minimalism, YAGNI principles, and root-cause fixes. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni"…

GulajavaMinistudio/awesome-copilot-id · 146 tokens

full-audit

Exhaustive, denominator-driven audit of an entire area (codebase, docs, memory, skills, DB, config). Runs a 6-phase pipeline: scope agreement + prior-map diff -> deterministic sweep (counts/versions/paths/parsing plus cross-index reconciliation) -> parallel read-only content review (citations forced, rule dry-run) ->…

AlexZio00/sovereign-skills · 205 tokens

tech-lead/code-review

A checklist-based method for examining code for correctness, security, performance, clarity, and ease of maintenance.

echoVic/boss-skill · 23 tokens