coordinate-agent-work

coordinate-agent-work is a skill for Claude Code, Codex from cambridgetcg/agenttool. It costs 95 tokens per session (2,587 once invoked), scanned A, original, Apache-2.0.

A coordination guide for running multiple coding or research agents across sessions and linked Git worktrees. It uses a shared local journal to record who is working and what has happened.

In plain words
What is it for?
Use it to start and reconnect agent sessions, divide parallel work, check updates, and manage agents from a central host.
Why use it?
It helps prevent agents from editing the same work, losing track of each other, or relying on outdated shared information.

Skill for Claude CodeCodex

Part of the agenttool-collab plugin — 2 skills shipped together

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.

agentmods
npx agentmods add skills/cambridgetcg/agenttool/coordinate-agent-work
Any agent
npx skills add cambridgetcg/agenttool --skill coordinate-agent-work
Clone the repo
git clone --depth 1 https://github.com/cambridgetcg/agenttool

Made for: Claude Code, Codex.

Or install agenttool-collab, the plugin that ships this one along with the rest of its 2 skills.

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 coordinate-agent-work

README.md
[![agentmods](https://agentmods.dev/badge/skills/cambridgetcg/agenttool/coordinate-agent-work.svg)](https://agentmods.dev/skills/cambridgetcg/agenttool/coordinate-agent-work)
Your own site
<a href="https://agentmods.dev/skills/cambridgetcg/agenttool/coordinate-agent-work"><img src="https://agentmods.dev/badge/skills/cambridgetcg/agenttool/coordinate-agent-work.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,587 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00095 $0.02587
Opus 5 $0.00048 $0.01293
Sonnet 5 $0.00019 $0.00517
Haiku 4.5 $0.00010 $0.00259

Measured 4d ago against content hash 77be94270d9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coordinate-agent-work 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 4d 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.

packages/collab/skills/coordinate-agent-work/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coordinate Agent Work

Use the journal as a compact coordination record. Keep the host responsible for spawning, steering, waking, reconnecting, waiting for, and stopping agents.

Start and reconcile

  1. Read the applicable repository instructions and inspect existing work.
  2. Call collab_session_start with the repository root once for each independent agent process or conversation. It opens the workspace, creates a credential-bound coordination session, and binds the MCP process. Never open or read the credential file. Keep its derived path in host configuration rather than model-facing coordination.
  3. Verify that every participant opened the intended workspace and shared database. Expect linked Git worktrees to share a repository workspace while retaining distinct worktree records.
  4. Poll with collab_next from the persisted session cursor at the start of each turn, after local work, before relying on shared state, and whenever the host wakes the agent. Omit event_limit for the 10-event MCP default or set an integer from 1 through 50. The limit bounds the event page and its routed reports, not the task, conflict, or handoff projections for the labelled snapshot head.
  5. Process one page before calling collab_cursor_ack with its exact terminal next_anchor ({ epoch_id, sequence, hash }), then poll again if has_more is true. A supplied known_cursor validates an anchor but does not paginate or acknowledge. Treat acknowledgement as “processed,” never as agreement, acceptance, consent, or correctness. Use collab_cursor_reset only for deliberate replay or recovery.

Use the separate presence plane only when discovery or compatibility needs it. Call collab_session_join with a workspace ID and self-declared labels, inspect routes with collab_session_list, refresh the hint with collab_session_heartbeat, and finish it with collab_session_leave. Treat the returned actor_key, runtime/model labels, capabilities, and live/stale state as routing hints, never credentials, health, identity, competence, permission, or proof that a model is running. A heartbeat never renews a task lease. A presence leave never calls collab_session_end, releases work, or ends the bound coordination session. Do not infer a linkage merely because the two planes share a label or workspace.

Read the full file on GitHub · 208 lines

Files

What ships with it

1 file 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.

  1. 4d ago First seen · 208 lines · 95 tokens per session scan A 77be94270d9e

Subscribe to this mod's changes

coordinate-agent-work is a skill published in the GitHub repository cambridgetcg/agenttool (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 95 tokens to every session and 2,587 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

add-a-service

Scaffold a new service under services/ in the builders-stack monorepo. Use when something needs its own URL, port, or independent deploy. Covers the package, entrypoint, config, Tilt, deployment registry, and shared small-image build path.

lonormaly/builders-stack · 55 tokens

design-a-schema

Model a new table (or reshape an existing one) in libs/db with Drizzle — normalize by default, add the right constraints, and index deliberately. Use when adding a table/column, deciding on keys and foreign keys, or when a query is slow because the schema or its indexes are wrong. Enforces the stack's "Drizzle is the…

lonormaly/builders-stack · 91 tokens

wire-a-new-payment-provider

Add or swap a payment provider behind the @stack/payment adapter in the builders-stack monorepo. Use when integrating Stripe, Paddle, Lemon Squeezy, or any provider alongside or in place of the default Creem adapter. The whole point is that apps and the API never change — only the adapter implementation does. Covers…

lonormaly/builders-stack · 92 tokens

ornn-agent-manual-cli

The manual an AI agent loads to operate Ornn — the model-agnostic skill-lifecycle API (an npm-style registry + CLI for agent skills) — via the NyxID CLI (nyxid proxy request ornn-api …). Load and follow this skill WHENEVER the user asks to do anything with Ornn skills or skillsets. Skills: search Ornn or find a skill…

ChronoAIProject/Ornn · 337 tokens

ornn-agent-manual-http

Operational manual for AI agents using the Ornn skill-lifecycle API via direct HTTPS with a NyxID bearer token (curl -H "Authorization: Bearer $TOKEN" …). Once loaded, the host agent can search / pull / execute / build / upload / share skills end-to-end. Authoritative contract between Ornn and the agent. Pair this…

ChronoAIProject/Ornn · 106 tokens

add-a-lib

Scaffold a new shared library under libs/ in the builders-stack monorepo. Use when code is needed in two or more places (apps or services) and should become a single source of truth consumed by package name. Covers the package.json, tsconfig, the one-public-door src/index.ts barrel, and wiring it into a consumer…

lonormaly/builders-stack · 81 tokens