thinking-steel-manning

thinking-steel-manning is a skill for Claude Code from tjboudreaux/cc-thinking-skills. It costs 31 tokens per session (718 once invoked), scanned A, original, MIT.

A decision-making method that presents the strongest fair version of an opposing view before accepting or rejecting a proposal. It then states what evidence or conditions would change the decision.

In plain words
What is it for?
Use it in design reviews, architecture debates, proposal assessments, and other situations where you need to test whether your preferred decision survives its best counterargument.
Why use it?
It reduces snap agreement, weak objections, and decisions based on misrepresenting the alternative. It is intended for choices where the trade-offs are real.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the cc-thinking-skills plugin — 28 skills shipped together

Good fit Use it in design reviews, architecture debates, proposal assessments, and other situations where you need to test whether your preferred decision survives its best counterargument.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tjboudreaux/cc-thinking-skills/thinking-steel-manning
About the project

Claude Code Thinking Skills is a catalogue of 28 portable skills that give coding agents structured procedures for reasoning about decisions, diagnosis, risk, strategy, and related problems. It is intended for Claude Code, GitHub Copilot, Codex, Cursor, and other tools that support Agent Skills.

tjboudreaux/cc-thinking-skills · 1,306 stars · on GitHub

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 tjboudreaux/cc-thinking-skills --skill thinking-steel-manning
Clone the repo
git clone --depth 1 https://github.com/tjboudreaux/cc-thinking-skills

Made for: Claude Code.

Or install cc-thinking-skills, the plugin that ships this one along with the rest of its 28 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 thinking-steel-manning

README.md
[![agentmods](https://agentmods.dev/badge/skills/tjboudreaux/cc-thinking-skills/thinking-steel-manning/github.svg)](https://agentmods.dev/skills/tjboudreaux/cc-thinking-skills/thinking-steel-manning)
Your own site
<a href="https://agentmods.dev/skills/tjboudreaux/cc-thinking-skills/thinking-steel-manning"><img src="https://agentmods.dev/badge/skills/tjboudreaux/cc-thinking-skills/thinking-steel-manning/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 thinking-steel-manning

Your own site · 80×15
<a href="https://agentmods.dev/skills/tjboudreaux/cc-thinking-skills/thinking-steel-manning"><img src="https://agentmods.dev/badge/skills/tjboudreaux/cc-thinking-skills/thinking-steel-manning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 718 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. Third-party audits
  • Socket pass 12 Mar 2026
  • Snyk pass 12 Mar 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00031 $0.00718
Opus 5 $0.00015 $0.00359
Sonnet 5 $0.00006 $0.00144
Haiku 4.5 $0.00003 $0.00072

Measured 12d ago against content hash 89c1401a5336, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

thinking-steel-manning 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/thinking-steel-manning/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Steel-Manning

Core rule: Engage the best form of the opposing case, not a weak one. If your position survives that, reaffirm; if not, update.

When to Use

  • About to reject a proposal, design, or alternative approach.
  • Inclined to agree with the user/plan and risk sycophancy — construct the best case against first.
  • Design review, architecture debate, or conflict where trade-offs are real.
  • Validating your own preferred decision before locking it (strongest-countercase check).

When NOT to Use

  • Settled fact, security anti-pattern, or violated hard requirement — correct it; do not invent a defense of what is wrong.
  • You already agree for stated, weighed reasons — do not perform a fake debate.
  • Trivial or fully reversible choices where deliberation cost exceeds downside.
  • Live emergency — act first; steel-man in the post-incident review.
  • Need definition/assumption cleanup, not opposition — use socratic.
  • Need failure scenarios for a plan — use pre-mortem; need attacker paths — use red-team.

Procedure

  1. State the target claim or decision you are about to accept or reject, in one sentence. Name the real alternative if one exists.
  2. Extract the core insight behind the opposing position (or against your preferred path): the legitimate concern even if the proposed solution is wrong.
  3. Construct the strongest faithful case an informed advocate would make: best evidence, incentives, and failure modes — no mockery, no cherry-picked weak version, no motive attacks. Include base rates or concrete alternatives that could overturn the preferred path when relevant.
  4. State agreement / overturn conditions. Write one observation or result that would make you accept the opposing case (or abandon your preferred path), and whether you have looked for it.
  5. Engage that strong version, then decide. Respond to the steel-manned case on the merits. Output one of: accept opposing path, revise synthesis, or reaffirm original with explicit residual risks. Naming the countercase without accept/revise/reaffirm is incomplete. Stop once the decision updates or is reaffirmed with conditions.

Read the full file on GitHub · 53 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. 12d ago First seen · 53 lines · 31 tokens per session scan A 89c1401a5336

Subscribe to this mod's changes

thinking-steel-manning is a skill published in the GitHub repository tjboudreaux/cc-thinking-skills (1,306 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 718 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 2026-08-30.

Related

Other skills, from other repositories

forensic-read

Read any document the way a detective reads a witness statement — surface what it is NOT saying. Unlike a summarizer (which tells you what a text says), this skill exposes the subtext: hedging and weasel words, conspicuous omissions, buried leads, frequency tells, tone shifts, and non-answers. Use it on earnings…

3243dwon/clear-eye · 170 tokens

pre-mortem

Find what will kill a plan before it's committed to — by assuming it already failed and working backwards to the causes. Based on Gary Klein's pre-mortem technique. Unlike generic "what are the risks?" brainstorming, this skill imagines a specific, vivid failure six months out, reasons back to the most likely causes…

3243dwon/clear-eye · 162 tokens

second-order

Reason past the obvious, first-order consequence to the second-, third-, and long-tail effects everyone else stops short of. Where most analysis says "X causes Y", this skill asks "and then what?" — mapping the cascade, surfacing the non-obvious winners and losers, the reflexive responses, and the effects that only…

3243dwon/clear-eye · 157 tokens

foundation-models

On-device LLM integration using Apple's Foundation Models framework. Use when implementing AI text generation, structured output, or tool calling.

rshankras/claude-code-apple-skills · 29 tokens

analytics-interpretation

Interpret app metrics and make data-driven decisions. Covers DAU/MAU, retention, LTV, ARPU, App Store Connect analytics, AARRR funnel analysis, cohort analysis, and diagnostic decision trees. Use when user wants to understand their metrics, diagnose problems, or build a data-driven growth plan.

rshankras/claude-code-apple-skills · 68 tokens

app-namer

Turn an app idea into validated, App-Store-ready name candidates. Use when the user says "name my app", "what should I call it", "app name ideas", "help me name this app", "is this name available", or needs to pick a brandable, ownable name before reserving it in App Store Connect.

rshankras/claude-code-apple-skills · 73 tokens