collaborating-agents-system

collaborating-agents-system is a skill for Claude Code, Codex from baochunli/pi-collaborating-agents. It costs 49 tokens per session (2,653 once invoked), scanned A, original, MIT.

An operating guide for coordinating a main coding agent with additional agents working on related tasks. It covers messaging, spawning agents, checking their sessions, and reserving files so multiple agents do not edit the same file at once.

In plain words
What is it for?
It is for running multi-agent coding workflows, inspecting subagent progress, sending messages, and coordinating file changes.
Why use it?
It gives agents shared rules for dividing work, communicating results, and avoiding conflicting edits.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit It is for running multi-agent coding workflows, inspecting subagent progress, sending messages, and coordinating file changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/baochunli/pi-collaborating-agents/collaborating-agents-system
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 baochunli/pi-collaborating-agents --skill collaborating-agents-system
Clone the repo
git clone --depth 1 https://github.com/baochunli/pi-collaborating-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.

agentmods badge for collaborating-agents-system

README.md
[![agentmods](https://agentmods.dev/badge/skills/baochunli/pi-collaborating-agents/collaborating-agents-system/github.svg)](https://agentmods.dev/skills/baochunli/pi-collaborating-agents/collaborating-agents-system)
Your own site
<a href="https://agentmods.dev/skills/baochunli/pi-collaborating-agents/collaborating-agents-system"><img src="https://agentmods.dev/badge/skills/baochunli/pi-collaborating-agents/collaborating-agents-system/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 collaborating-agents-system

Your own site · 80×15
<a href="https://agentmods.dev/skills/baochunli/pi-collaborating-agents/collaborating-agents-system"><img src="https://agentmods.dev/badge/skills/baochunli/pi-collaborating-agents/collaborating-agents-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,653 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 $0.00049 $0.02653
Opus 5.5 $0.00020 $0.01061
Sonnet 5.5 $0.00010 $0.00531
Haiku 4.5 $0.00005 $0.00265

Measured 2mo ago against content hash f3fde043e0d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

collaborating-agents-system 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 2mo 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.

skills/collaborating-agents-system/SKILL.md · 297 lines

How it starts

The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Collaborating Agents System (Coordinator + Subagent Playbook)

Use this skill when operating the collaborating-agents extension so coordinators and subagents follow the same protocol.

What this system provides

The extension gives you:

  1. Agent mesh + messaging via agent_message
  2. File reservation locking for write/edit coordination
  3. Subagent spawning via subagent

Core tools

1) agent_message (coordination + reservations)

Actions:

  • status — self identity, focus, peer count, reservations
  • list — active agents
  • sessions — scoped subagent run/session records; completed/failed included by default, use includeCompleted: false for active only
  • session — resolve one subagent run/session record
  • tail — read a concise transcript tail for one subagent run/session
  • send — direct message to one peer (to, message, optional replyTo, optional urgent)
  • broadcast — message all peers (message, optional urgent)
  • feed — recent global message log (limit, default 20, max 400)
  • thread — DM history with one peer (to, optional limit)
  • reserve — reserve write/edit targets (paths, optional reason)
  • release — release specific paths, or all if omitted

Delivery semantics (important):

  • Normal messages (urgent: false or omitted) are delivered with Pi followUp (queued until the current turn completes).
  • Urgent messages (urgent: true) are delivered with Pi steer (interrupt immediately).

Common calls:

agent_message({ action: "status" })
agent_message({ action: "list" })
agent_message({ action: "sessions" })
agent_message({ action: "sessions", includeCompleted: false })
agent_message({ action: "session", runId: "subagent-run-id" })
agent_message({ action: "tail", runId: "subagent-run-id" })
agent_message({ action: "tail", to: "latest" })
agent_message({ action: "send", to: "BlueFalcon", message: "Started task X" })
agent_message({ action: "send", to: "BlueFalcon", message: "Need decision now", urgent: true })
agent_message({ action: "broadcast", message: "Wave 2 complete" })
agent_message({ action: "thread", to: "BlueFalcon", limit: 20 })
agent_message({ action: "reserve", paths: ["src/server/"], reason: "auth refactor" })
agent_message({ action: "release", paths: ["src/server/"] })

Read the full file on GitHub · 297 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. 2mo ago First seen · 297 lines · 49 tokens per session scan A f3fde043e0d2

Subscribe to this mod's changes

collaborating-agents-system is a skill published in the GitHub repository baochunli/pi-collaborating-agents (28 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 2,653 once invoked, about $0.0002 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 2026-08-30.

Related

collaborating-agents-system compared with skills from other repositories

collaborating-agents-system next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
collaborating-agents-systembaochunli/pi-collaborating-agentsSkill284mo agoMITA49Claude Code, Codex
imagegenopenai/codexSkill135ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill100ktodayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill80k6d agoMITA200Claude Code, Codex
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
systematic-debuggingobra/superpowersSkill317k9d agoMITA21Claude Code