claude-collaboration

claude-collaboration is a skill for Claude Code, Codex from davidYichengWei/Agency. It costs 62 tokens per session (1,018 once invoked), scanned A, original, MIT.

A workflow for having Codex and Anthropic's Claude model review work or solve a problem independently and then compare their results.

In plain words
What is it for?
Use it for code reviews, design or requirements work, investigations, and multi-round review where Claude's session can be continued.
Why use it?
It adds a second model's perspective for finding issues, reducing missed problems, and checking whether fixes address earlier concerns.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it for code reviews, design or requirements work, investigations, and multi-round review where Claude's session can be continued.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/davidyichengwei/agency/claude-collaboration
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 davidYichengWei/Agency --skill claude-collaboration
Clone the repo
git clone --depth 1 https://github.com/davidYichengWei/Agency

Made for: Claude Code, Codex.

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 claude-collaboration

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidyichengwei/agency/claude-collaboration/github.svg)](https://agentmods.dev/skills/davidyichengwei/agency/claude-collaboration)
Your own site
<a href="https://agentmods.dev/skills/davidyichengwei/agency/claude-collaboration"><img src="https://agentmods.dev/badge/skills/davidyichengwei/agency/claude-collaboration/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 claude-collaboration

Your own site · 80×15
<a href="https://agentmods.dev/skills/davidyichengwei/agency/claude-collaboration"><img src="https://agentmods.dev/badge/skills/davidyichengwei/agency/claude-collaboration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,018 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 $0.00062 $0.01018
Opus 5 $0.00031 $0.00509
Sonnet 5 $0.00012 $0.00204
Haiku 4.5 $0.00006 $0.00102

Measured 10d ago against content hash 837d7fbfb332, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

claude-collaboration 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 10d 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.

shared/skills/claude-collaboration/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Collaboration

Collaboration Modes

Review mode - Codex works, Claude reviews:

  • Use for: code changes, final checks before gates
  • Codex completes work -> sends paths, diffs, or task context to Claude for review
  • For code review: ask Claude to review critically and cite specific file/line evidence
  • For designs/plans: Claude reviews directly as an independent reviewer

Parallel mode - both agents work independently, then compare:

  • Use for: requirements drafting, design proposals, RCA investigation, complex problem-solving
  • Codex and Claude both work the problem independently -> compare results -> synthesize
  • Avoids anchoring bias - Claude should not see Codex's answer before producing its own position

Consensus Protocol

Consensus means Claude explicitly confirms it has no remaining concerns. Fixing issues and assuming consensus is NOT consensus - you must send your changes back to Claude and get explicit approval.

Review mode loop

  1. Claude reviews -> provides findings
  2. You address the findings (fix code, update design, or argue why a finding is wrong)
  3. Resume the session and ask Claude to re-review your changes
  4. Claude confirms all issues resolved -> consensus reached -> proceed
  5. Claude raises new/remaining issues -> go to step 2 (max 3 rounds)
  6. After 3 rounds with unresolved disagreements -> escalate to user with both positions

Parallel mode loop

  1. Both work independently -> compare results
  2. Identify agreements and disagreements
  3. For disagreements: each side argues with evidence -> converge on a unified position
  4. If cannot converge (max 3 rounds) -> escalate to user with both positions

The loop is not optional. Never skip re-review. Never declare consensus unilaterally. Claude must say it is satisfied.

Session Management

  • New session: Start a fresh session for each task in tasks.md, or when switching to a fundamentally different topic (e.g., from design review to code review).
  • Resume: Within the same task or topic, always resume the existing session. Claude retains full context - starting fresh loses valuable conversation history.
  • Session ID: Let Claude create the first session, record the emitted session_id, then use --resume "$SESSION_ID" for follow-ups. Use an explicit --session-id only when the caller cannot parse Claude's output before the next round.

Read the full file on GitHub · 94 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. 10d ago First seen · 94 lines · 62 tokens per session scan A 837d7fbfb332

Subscribe to this mod's changes

claude-collaboration is a skill published in the GitHub repository davidYichengWei/Agency (5 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 1,018 once invoked, about $0.0003 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.