cross-examination

cross-examination is a skill for Claude Code from supportersimulator/3-surgeons. It costs 21 tokens per session (1,128 once invoked), scanned A, original, MIT.

A three-stage review in which multiple AI models independently examine a claim, challenge one another, and produce a combined conclusion.

In plain words
What is it for?
Use it for major architecture decisions, high-risk changes involving authentication or payments, database or shared-interface changes, and persistent bugs.
Why use it?
It provides a more careful way to examine decisions when evidence conflicts, the cause of a bug is unclear, or a change could have broad consequences.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the 3-surgeons plugin — 23 skills, 7 commands, 1 agent, 3 hooks, 1 MCP server shipped together

Good fit Use it for major architecture decisions, high-risk changes involving authentication or payments, database or shared-interface changes, and persistent bugs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/supportersimulator/3-surgeons/cross-examination
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 supportersimulator/3-surgeons --skill cross-examination
Clone the repo
git clone --depth 1 https://github.com/supportersimulator/3-surgeons

Made for: Claude Code.

Or install 3-surgeons, the plugin that ships this one along with the rest of its 23 skills, 7 commands, 1 agent, 3 hooks, 1 MCP server.

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 cross-examination

README.md
[![agentmods](https://agentmods.dev/badge/skills/supportersimulator/3-surgeons/cross-examination/github.svg)](https://agentmods.dev/skills/supportersimulator/3-surgeons/cross-examination)
Your own site
<a href="https://agentmods.dev/skills/supportersimulator/3-surgeons/cross-examination"><img src="https://agentmods.dev/badge/skills/supportersimulator/3-surgeons/cross-examination/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 cross-examination

Your own site · 80×15
<a href="https://agentmods.dev/skills/supportersimulator/3-surgeons/cross-examination"><img src="https://agentmods.dev/badge/skills/supportersimulator/3-surgeons/cross-examination.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,128 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 $0.00021 $0.01128
Opus 5 $0.00010 $0.00564
Sonnet 5 $0.00004 $0.00226
Haiku 4.5 $0.00002 $0.00113

Measured 9d ago against content hash e6fb0f6ae9f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cross-examination 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 9d 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/cross-examination/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Examination

When to Trigger

Cross-examination is the heavyweight tool. Use it when the stakes justify the cost and latency:

  • Major architectural decisions -- changing core data flow, adding new subsystems, restructuring modules
  • Conflicting evidence -- two sources disagree, logs contradict expectations, behavior is non-deterministic
  • High-risk changes -- touching authentication, payment flows, safety systems, production data
  • Wide-impact changes -- modifying >3 files, changing shared interfaces, altering database schemas
  • Persistent bugs -- root cause unclear after 15+ minutes of investigation

Do NOT use for: trivial fixes, style changes, single-file edits with clear scope, questions with obvious answers.

How to Invoke

CLI

3s cross-exam "Should we migrate from REST to GraphQL for the patient API?"

MCP Tool

cross_examine(topic="Should we migrate from REST to GraphQL for the patient API?", depth="full")

The depth parameter defaults to "full" (3-phase). There is currently one depth level; future versions may support "quick".

The 3-Phase Process

Phase 1: Independent Analysis

Both the Cardiologist (GPT-4.1-mini) and Neurologist (Qwen3-4B) analyze the topic independently. Neither sees the other's work. This prevents anchoring bias -- each model forms its own opinion from scratch.

Phase 2: Cross-Review

Each surgeon reviews the other's Phase 1 analysis. The Cardiologist reviews the Neurologist's work, looking for weaknesses, blind spots, and errors. The Neurologist does the same for the Cardiologist. This adversarial review is where most value is generated.

Phase 3: Synthesis

The Cardiologist (broader perspective from the external API model) synthesizes both analyses and both cross-reviews into a final report. The synthesis explicitly emphasizes disagreements -- where the surgeons diverge is the most valuable signal.

Interpreting Results

The result contains four key fields:

Read the full file on GitHub · 109 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. 9d ago First seen · 109 lines · 21 tokens per session scan A e6fb0f6ae9f9

Subscribe to this mod's changes

cross-examination is a skill published in the GitHub repository supportersimulator/3-surgeons (2 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 1,128 once invoked, about $0.0001 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

skill-creator

Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.

zhayujie/CowAgent · 61 tokens

image-generation

Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.

zhayujie/CowAgent · 41 tokens

deepcode-self-refer

Answers questions about Deep Code CLI itself — including features, configuration options, slash commands, Skills, MCP integration, permissions, notifications, session persistence, and troubleshooting. Use this when users ask how to configure or use Deep Code, how to set up an MCP server, configure notifications (such…

lessweb/deepcode-cli · 86 tokens

skill-writer

Guide users through creating, updating, debugging, and validating Agent Skills for AI agents. Use when the user wants to create, write, author, design, troubleshoot, validate, or improve a Skill, or needs help with SKILL.md, frontmatter, or skill structure.

lessweb/deepcode-cli · 59 tokens

image-generator

Generate or edit images from text and local files, image URLs, or data URLs through image API. Use when the user asks to create an image, generate from one or more reference images, combine styles or elements across references, or edit a marked region while blending the result into the original scene.

lessweb/deepcode-cli · 62 tokens

weibo-poster

A writing guide for Weibo, a Chinese microblogging platform similar to a short-post social network. It covers concise posts, longer posts, hashtags, @ mentions, image layouts, and posting-time suggestions.

dongsheng123132/u-claw · 32 tokens