What is dev-collaboration?

A role-based teamwork process for coding agents with three jobs: a Drafter creates the work, a Reviewer checks it, and a Breaker tries to find problems. The roles and their sequence are assigned through prompts.

Use it to divide a development task among agents, produce an artifact, review it, and actively look for weaknesses or failures.

It gives collaborative development a repeatable order and separates creation from checking. This makes errors and missing requirements easier to identify before work is accepted.

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

Your own site

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

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,391 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	$0.00037	$0.01391
Opus 5.5	$0.00015	$0.00556
Sonnet 5.5	$0.00007	$0.00278
Haiku 4.5	$0.00004	$0.00139

Measured 1mo ago against content hash 4ee43b678f3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dev-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/dev-collaboration/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev Collaboration Pattern

Use mesh-comms-core first if direct peer notification has not already been proven. This skill defines roles and sequence; mesh-comms-core defines the transport.

Default roster: assign roles to Claude Code and Codex peers. Do not launch, recruit, or assign Gemini CLI, Antigravity CLI, or Antigravity Desktop unless the human prompt explicitly names that peer.

Prerequisites

Notification Scripts: Use the repo's agent-specific scripts under interlateral_dna/ to send direct notifications.
- Claude Code: node interlateral_dna/cc.js send "message"
- Codex: node interlateral_dna/codex.js send "message"
- Gemini, only when explicitly selected: node interlateral_dna/gemini.js send "message"
- Antigravity CLI, only when explicitly selected: node interlateral_dna/agy.js send "message"
Ledger: Use comms.md as the shared communications ledger. Posting to comms.md alone does not wake a peer.

Roles

Role	Job	Deliverable
DRAFTER	Creates or modifies the artifact	Working draft at the specified `artifact_path`
REVIEWER	Reviews for correctness, clarity, completeness	List of actionable suggestions
BREAKER	Adversarial testing; finds flaws, edge cases, failure modes	List of ways the artifact could break

Any explicitly selected v0.1 peer may hold any role. In routine use, choose Claude Code and Codex; treat Gemini and Antigravity as special opt-in peers.

Prompt Requirements

Every invocation of this skill MUST include:

Explicit role assignment -- which agent holds which role(s).
artifact_path -- the file path for the artifact being created or reviewed.

Dual-Hatting Rule

All three roles must be covered. If only two agents are available, the prompt MUST explicitly assign one agent a dual-hatted role. Example:

Codex is both REVIEWER and BREAKER.

The dual-hatted agent must complete each role as a separate phase and deliver separate outputs for each.

Read the full file on GitHub · 154 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 · 154 lines · 37 tokens per session scan A 4ee43b678f3e

Subscribe to this mod's changes

dev-collaboration is a skill published in the GitHub repository dazzaji/interlateral_agents (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,391 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

dev-collaboration next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dev-collaborationdazzaji/interlateral_agents	Skill	11	10d ago	Apache-2.0	A	37	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