What is ready-rock-quartet?

A four-agent team setup with fixed roles: lead, reviewer, breaker, and verifier. It starts a visible terminal team and keeps each agent's responsibilities explicit.

Use it for a concrete task or command sequence that needs one lead plus separate review, failure-finding, and verification roles.

It prevents agents from working at cross-purposes or exploring prematurely when a coordinated execution plan is needed. The human can see and interact with each terminal.

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/ready-rock-quartet/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/ready-rock-quartet/github.svg)](https://agentmods.dev/skills/dazzaji/interlateral_agents/ready-rock-quartet)

Your own site

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

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,261 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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	$0.00045	$0.03261
Opus 5.5	$0.00018	$0.01304
Sonnet 5.5	$0.00009	$0.00652
Haiku 4.5	$0.00005	$0.00326

Measured 1mo ago against content hash df0c5ba7f9d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

ready-rock-quartet scanned grade B with 1 finding 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

If different session names are used, lock them explicitly in the sprint prompt.

.agent/skills/ready-rock-quartet/SKILL.md · 433 lines

How it starts

The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ready Rock Quartet

Purpose

Use this skill when you need a four-agent execution team that humans can see and type into directly.

This pattern is optimized for:

visible terminal boot
explicit role lock
clean peer-to-peer comms
a single lead with three support roles
preventing non-lead agents from improvising while waiting for coordination

Use mesh-comms-core for the transport layer before relying on this workflow. This skill assumes live direct-send plus ledger behavior already works.

This is the house pattern for:

LEAD
REVIEWER
BREAKER
VERIFIER

When To Use

Use this skill when all of the following are true:

you want exactly four live agents
the human should be able to see each terminal
the team needs explicit role ownership
the task has a real execution artifact or command sequence to review
premature side exploration would be risky

Do not use this skill for:

two-agent drafting
blind headless swarms
loose brainstorming without a concrete artifact

Recommended Team Shape

Preferred roster:

Codex as LEAD
Claude as REVIEWER
Codex as BREAKER
Claude as VERIFIER

Do not substitute Gemini CLI, Antigravity CLI, or Antigravity Desktop into the quartet unless Principal Human explicitly selects that peer for this run.

Recommended session naming:

13-codex-lead -> LEAD
13-claude-reviewer -> REVIEWER
13-codex-breaker -> BREAKER
13-claude-verifier -> VERIFIER

Why this naming is better:

it avoids collisions with already-running ia-* house sessions
the role is obvious from the session name
the 13- prefix ties the team to Skill 13 and makes the quartet easy to spot in tmux

If different session names are used, lock them explicitly in the sprint prompt.

House Bootstrap Recipe

In this repo, the practical launch path is:

./scripts/launch-codex-peer.sh 13-codex-lead "Read AGENTS.md first, then wait for instructions."
./scripts/launch-codex-peer.sh 13-codex-breaker "Read AGENTS.md first, then wait for instructions."
./scripts/launch-cc-peer.sh 13-claude-reviewer "Read CLAUDE.md first, then wait for instructions."
./scripts/launch-cc-peer.sh 13-claude-verifier "Read CLAUDE.md first, then wait for instructions."

Read the full file on GitHub · 433 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 · 433 lines · 45 tokens per session scan B df0c5ba7f9d2

Subscribe to this mod's changes

ready-rock-quartet is a skill published in the GitHub repository dazzaji/interlateral_agents (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 45 tokens to every session and 3,261 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-03.

Building agents

ready-rock-quartet next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ready-rock-quartetdazzaji/interlateral_agents	Skill	11	10d ago	Apache-2.0	B	45	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	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
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code

interlateral_agents: Skill for Claude Code