What is peer-collaboration?

A turn-based workflow in which two agents create and refine one artifact together until both agree it is complete.

Use it for collaborative drafting and iterative refinement of a shared document or other concrete artifact.

It gives each agent a chance to propose changes, challenge the other, and respond before the work is finished. This avoids treating one agent as the sole authority.

How dazzaji/interlateral_agents configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to dazzaji/interlateral_agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dazzaji/interlateral_agents/main/.agent/skills/peer-collaboration/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/dazzaji/interlateral_agents

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dazzaji/interlateral_agents/peer-collaboration/github.svg)](https://agentmods.dev/skills/dazzaji/interlateral_agents/peer-collaboration)

Your own site

<a href="https://agentmods.dev/skills/dazzaji/interlateral_agents/peer-collaboration"><img src="https://agentmods.dev/badge/skills/dazzaji/interlateral_agents/peer-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dazzaji/interlateral_agents/peer-collaboration"><img src="https://agentmods.dev/badge/skills/dazzaji/interlateral_agents/peer-collaboration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 862 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.

Model	Per session	Once invoked
Fable 5.1	$0.00020	$0.00862
Opus 5.5	$0.00008	$0.00345
Sonnet 5.5	$0.00004	$0.00172
Haiku 4.5	$0.00002	$0.00086

Measured 1mo ago against content hash c1afa004e762, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

peer-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 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.

.agent/skills/peer-collaboration/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Peer Collaboration

Purpose

Two agents work together as equals to co-create a single artifact. They take turns proposing, reacting, and refining until both agree the work is complete.

Use mesh-comms-core first if direct peer notification has not already been proven. comms.md is the ledger, not the wake-up path.

Default roster: use Claude Code and Codex peers. Do not substitute or add Gemini CLI, Antigravity CLI, or Antigravity Desktop unless the human prompt explicitly names that peer.

Roles

Role	Description
`PEER_A`	Initiates the first draft, proposes ideas
`PEER_B`	Responds, modifies, extends, challenges

Both roles are equal. Either can propose changes. Neither has authority over the other.

Protocol

1. PEER_A proposes initial draft (2-3 key points or sections)
2. PEER_B reacts: agrees, modifies, or challenges; adds 1-2 points
3. PEER_A responds to feedback, refines draft
4. Continue alternating until BOTH signal [DONE]

Turn Format

Each turn should include:

What you're adding/changing
Why (brief rationale)
The updated artifact (or diff)

Termination

Either agent may propose [DONE] when they believe the artifact is complete
The other agent must confirm with [DONE] to end
If the other agent disagrees, they explain why and the iteration continues

Inputs

All inputs come from the prompt. No structured inputs required.

Optional:

output: File path to save the final artifact
work: File path containing detailed requirements
max_turns: Override default (20)

Prompt Format Examples

Minimal:

Build a todo API spec. Use peer-collaboration. CC + CX.

With output:

Use peer-collaboration to write a haiku about recursion.
CC is PEER_A, CX is PEER_B.
Output: projects/haiku/recursion.md

With work file:

Use peer-collaboration.
Work: projects/api/requirements.md
CC is PEER_A, CX is PEER_B.
Output: projects/api/spec.md

Safety

Read the full file on GitHub · 132 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.

1mo ago First seen · 132 lines · 20 tokens per session scan A c1afa004e762

Subscribe to this mod's changes

peer-collaboration is a skill published in the GitHub repository dazzaji/interlateral_agents (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 20 tokens to every session and 862 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 2026-10-03.

Building agents

peer-collaboration next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
peer-collaborationdazzaji/interlateral_agents	Skill	11	10d ago	Apache-2.0	A	20	Claude Code, Codex
imagegenopenai/codex	Skill	133k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex

interlateral_agents: Skill for Claude Code