What is relay-room-collaboration?

A guided collaboration process where the current coding session does the implementation while another tool, Antigravity, plans and reviews the work without editing it.

Use it for large coding, design, refactoring, debugging, documentation, media, data, or multi-file tasks that need planning, read-only review, progress records, and published outputs.

It gives complex or high-risk projects a bounded, recorded review loop while keeping one session responsible for making changes.

relay-room-collaboration — Skill for Codex by w48669664-bit

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 w48669664-bit/colla-agent --skill relay-room-collaboration

Clone the repo

git clone --depth 1 https://github.com/w48669664-bit/colla-agent

Made for: 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/w48669664-bit/colla-agent/relay-room-collaboration/github.svg)](https://agentmods.dev/skills/w48669664-bit/colla-agent/relay-room-collaboration)

Your own site

<a href="https://agentmods.dev/skills/w48669664-bit/colla-agent/relay-room-collaboration"><img src="https://agentmods.dev/badge/skills/w48669664-bit/colla-agent/relay-room-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/w48669664-bit/colla-agent/relay-room-collaboration"><img src="https://agentmods.dev/badge/skills/w48669664-bit/colla-agent/relay-room-collaboration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,272 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	$0.00130	$0.01272
Opus 5	$0.00065	$0.00636
Sonnet 5	$0.00026	$0.00254
Haiku 4.5	$0.00013	$0.00127

Measured 10d ago against content hash 97308bc4e48d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

relay-room-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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/relay-room.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/relay-room-collaboration/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Colla Agent Collaboration

Keep the current Codex session as the only implementation agent. Use the bundled Relay Room runtime to open Colla Agent, consult Antigravity read-only, record observable work, and publish produced artifacts. Never invoke codex, codex exec, a subagent, or another recursive agent session from this workflow.

Prepare

Resolve the absolute path to scripts/relay-room.mjs from this Skill directory.
Read the target project's AGENTS.md and relevant instructions.
Inspect the worktree before editing. Preserve unrelated user changes.
Choose a review cap:
- explicit user choice wins;
- quick or simple: 3;
- standard/default: 5;
- deep or high-risk: 8;
- maximum audit: 12.
Start Relay Room for the current project and complete task brief:

node <skill-dir>/scripts/relay-room.mjs start \
  --project <absolute-project-root> \
  --task "<complete user request>" \
  --title "<short reader-facing mission title>" \
  --rounds 5

The command starts or reuses the local dashboard and opens it automatically. Give the dashboard URL to the user in the next progress update.

Plan with Antigravity

Run:

node <skill-dir>/scripts/relay-room.mjs consult plan

Read the returned JSON. Treat it as colleague advice, not authority. Resolve conflicts against the user request and project instructions. The CLI records the prompt, explicit rationale, questions, output, and adaptive review budget. Do not request or claim private chain-of-thought.

Implement as the current Codex

Record the start of implementation:

node <skill-dir>/scripts/relay-room.mjs event \
  --actor codex --stage implement --kind status --status running \
  --title "Codex is implementing" \
  --content "<concise implementation plan>"

Use normal Codex tools to edit the target project. Do not run a nested Codex CLI. Keep the Colla Agent Codex workstream alive while working. Before and after each meaningful inspection, decision, edit group, and verification, record one short public activity event:

Read the full file on GitHub · 152 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

10d ago First seen · 152 lines · 130 tokens per session scan A 97308bc4e48d

Subscribe to this mod's changes

relay-room-collaboration is a skill published in the GitHub repository w48669664-bit/colla-agent (2 stars, last pushed 3d ago), licensed MIT. It adds 130 tokens to every session and 1,272 once invoked, about $0.0006 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.

Building agents Multi-Agent Planning ai-agents antigravity codex developer-tools local-first

relay-room-collaboration

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Colla Agent Collaboration

Prepare

Plan with Antigravity

Implement as the current Codex

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

agent-harness-fault-injection

config-validator

aiwg-regenerate-copilot

artifact-metadata

hook-regenerate

link-check