steelman-then-break

steelman-then-break is a skill for Claude Code from Osipchuk/agent-skills. It costs 194 tokens per session (748 once invoked), scanned A, original, MIT.

A two-pass reviewer for design proposals and technology choices. It first builds the strongest case for an idea, then looks for the strongest reasons it could fail.

In plain words
What is it for?
Use it to evaluate architecture, tools, and other technical proposals. It identifies failure modes, names relevant anti-patterns, and ends objections with signals to watch for.
Why use it?
It separates support from criticism, making it easier to judge an idea without mixing enthusiasm and objections together. It can also compare problems with documented failures in the project.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the skills plugin — 8 skills shipped together

Good fit Use it to evaluate architecture, tools, and other technical proposals. It identifies failure modes, names relevant anti-patterns, and ends objections with signals to watch for.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/osipchuk/agent-skills/steelman-then-break
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 Osipchuk/agent-skills --skill steelman-then-break
Clone the repo
git clone --depth 1 https://github.com/Osipchuk/agent-skills

Made for: Claude Code.

Or install skills, the plugin that ships this one along with the rest of its 8 skills.

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 steelman-then-break

README.md
[![agentmods](https://agentmods.dev/badge/skills/osipchuk/agent-skills/steelman-then-break/github.svg)](https://agentmods.dev/skills/osipchuk/agent-skills/steelman-then-break)
Your own site
<a href="https://agentmods.dev/skills/osipchuk/agent-skills/steelman-then-break"><img src="https://agentmods.dev/badge/skills/osipchuk/agent-skills/steelman-then-break/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 steelman-then-break

Your own site · 80×15
<a href="https://agentmods.dev/skills/osipchuk/agent-skills/steelman-then-break"><img src="https://agentmods.dev/badge/skills/osipchuk/agent-skills/steelman-then-break.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 194 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 748 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 $0.00194 $0.00748
Opus 5 $0.00097 $0.00374
Sonnet 5 $0.00039 $0.00150
Haiku 4.5 $0.00019 $0.00075

Measured 12d ago against content hash e62e72fc6266, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

steelman-then-break 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 12d 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.

skills/steelman-then-break/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

steelman-then-break

Most design discussions die at "this seems good, ship it" because being the contrarian is socially expensive. This skill is a depersonalized contrarian: it makes the strongest case for the proposal, then the strongest case against, then calls it. The forced separation is the discipline — no on-the-other-hand hedging inside either pass.

Workflow

  1. Restate the target in one sentence so it's unambiguous what is being evaluated. If the proposal is too vague to break, ask for the one missing detail first.

  2. Pass 1 — Steelman. The strongest case for, including benefits the author may have missed. No "but", no caveats in this section. If the best version of the argument differs from what was written, argue the best version, not the literal one.

  3. Pass 2 — Break. The strongest case against. Lead with what breaks first. Name the failure mode or anti-pattern explicitly. When the project has a scars file (.claude/scars.md at the repo root — the team's catalogued past failures), cite the relevant precedent — arguing from the team's own evidence is the point. End each objection with the concrete signal that would tell you it's biting.

  4. Verdict. Calibrated, not reflexively negative. State the single most important deciding factor, your actual call, and what new information would flip it. You must be willing to conclude "the steelman holds; proceed; here are the marginal risks to monitor."

Calibration

Reflexive contrarianism is the failure mode that kills this skill. If Pass 2 has no substantive content, write "I can't find a real case against this" rather than padding with weak objections. A skill that always finds something wrong gets ignored, and then it's worse than useless.

The scars file lives in the project repo at .claude/scars.md — NOT inside this skill's folder, so the team can edit and version it without touching the installed (checksummed) skill. It logs patterns that failed before, so the Break pass argues from evidence instead of generic risk. references/scars.md in this skill is the format template with a worked example: copy it to .claude/scars.md when the team logs its first scar. No scars file just means the Break pass leans on named anti-patterns instead.

Read the full file on GitHub · 52 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. 12d ago First seen · 52 lines · 194 tokens per session scan A e62e72fc6266

Subscribe to this mod's changes

steelman-then-break is a skill published in the GitHub repository Osipchuk/agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 194 tokens to every session and 748 once invoked, about $0.0010 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.