Borrowing it
Nothing to install: this file belongs to mindroom-ai/mindroom. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mindroom-ai/mindroom/main/.claude/skills/code-debate/SKILL.mdgit clone --depth 1 https://github.com/mindroom-ai/mindroomWrote 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/mindroom-ai/mindroom/code-debate)<a href="https://agentmods.dev/skills/mindroom-ai/mindroom/code-debate"><img src="https://agentmods.dev/badge/skills/mindroom-ai/mindroom/code-debate/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/mindroom-ai/mindroom/code-debate"><img src="https://agentmods.dev/badge/skills/mindroom-ai/mindroom/code-debate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 32 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 138 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 164 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 86 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00035 | $0.03889 |
| Opus 5.5 | $0.00014 | $0.01556 |
| Sonnet 5.5 | $0.00007 | $0.00778 |
| Haiku 4.5 | $0.00003 | $0.00389 |
Grade A, and why
code-debate 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 1mo 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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Debate Protocol
A protocol for two coding agents (Claude Code, Gemini CLI, Codex, or any other) to debate code changes through a shared file (DEBATE.md). Both agents receive this same prompt. Role is determined by the first argument.
This skill assumes the two debate participants are started externally by a human in separate sessions. It is not a peer-orchestration skill.
How to use
Open two terminal tabs with coding agents (same or different). Invoke this skill in each, specifying role and subject:
/code-debate A <subject>— opener, createsDEBATE.mdwith the first analysis/code-debate B <subject>— responder, waits forDEBATE.mdthen replies
Role detection
Your role is determined by the first argument ($0):
A→ you are Agent A (opener). CreateDEBATE.mdand write the opening position.B→ you are Agent B (responder). Poll and wait forDEBATE.mdto exist, then read it and respond.
If no role argument is provided, fall back to file existence:
- If
DEBATE.mddoes not exist → you are Agent A (opener). - If
DEBATE.mdalready exists → you are Agent B (responder).
Do not ask the user which role to play.
Non-simulation guardrails (MUST)
- Never write content for the opposite role.
- Never simulate, fabricate, or placeholder the other agent's response.
- Never append both sides of a debate from one process.
- Never create, spawn, launch, delegate to, summon, or recruit the opposite debate role.
- Never use
spawn_agent,send_input, tmux supervision, background shell automation, or any other tool to manufacture the missing peer. - Role is immutable for the run: once detected as Agent A or Agent B, keep that role until
## CONSENSUS. - If you are about to write the opposite role, stop and report protocol violation instead of writing.
- After appending your section, only poll.
- Append another turn only after consuming the expected signed peer turn, even if it arrived before polling started.
- Without an unconsumed peer turn, keep polling until timeout or
## CONSENSUS. - On timeout, use
APPEND_TIMEOUTto close any unfinished fence and publish only a timeout## CONSENSUSfrom your own role.
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.
- 1mo ago Changed · +89 lines fa11c71754d0
- 1mo ago First seen · 236 lines · 35 tokens per session scan A 5accf458a245
code-debate is a skill published in the GitHub repository mindroom-ai/mindroom (347 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 3,889 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
code-review
A code-review checklist for examining code without rewriting it. It checks correctness, security, readability and performance, then labels findings by seriousness.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
meta-codereview-current-diff
Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCKWITHOVERRIDE / PASSWITHNOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.
review-pr
Review a pull request for code quality and security issues. Use when the user wants to review a PR, check PR code changes, or audit a pull request. Triggers on: "review PR", "review pull request", "check this PR", "the review-pr skill".
binary-triage
Performs initial binary triage by surveying memory layout, strings, imports/exports, and functions to quickly understand what a binary does and identify suspicious behavior. Use when first examining a binary, when user asks to triage/survey/analyze a program, or wants an overview before deeper reverse engineering.
deep-review
Parallel competency-based code review. Launches independent Agent reviewers per competency (security, performance, architecture, database, concurrency, error-handling, frontend, testing), each with a focused checklist and isolated context. Synthesizes findings into unified report with FIX/DEFER/ACCEPT triage. Use…