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 skills add adonai-labs/agent-runway --skill contrariangit clone --depth 1 https://github.com/adonai-labs/agent-runwayWrote 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.
[](https://agentmods.dev/skills/adonai-labs/agent-runway/contrarian)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.)
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.
- 11d ago First seen · 129 lines · 44 tokens per session scan A 1c0ae18fad5f
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.
Other skills, from other repositories
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
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.
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.
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"…
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) ->…
tech-lead/code-review
A checklist-based method for examining code for correctness, security, performance, clarity, and ease of maintenance.