coordinate-agent-work-hermes

coordinate-agent-work-hermes is a skill for Claude Code from cambridgetcg/agenttool. It costs 72 tokens per session (1,415 once invoked), scanned A, original, Apache-2.0.

Instructions for coordinating Hermes with other local AI coding agents through AgentTool Collab. They distinguish a credential-bound coordination system from a separate, optional presence and discovery system.

In plain words
What is it for?
Use them to start and end coordinated sessions, claim or review tasks, exchange reports and handoffs, track cursors, and optionally discover available peers.
Why use it?
They clarify which coordination method supports resumable work and evidence, and prevent self-declared presence from being mistaken for identity or permission.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

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

Good fit Use them to start and end coordinated sessions, claim or review tasks, exchange reports and handoffs, track cursors, and optionally discover available peers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cambridgetcg/agenttool/coordinate-agent-work-hermes
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 cambridgetcg/agenttool --skill coordinate-agent-work-hermes
Clone the repo
git clone --depth 1 https://github.com/cambridgetcg/agenttool

Made for: Claude Code.

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-hermes

README.md
[![agentmods](https://agentmods.dev/badge/skills/cambridgetcg/agenttool/coordinate-agent-work-hermes.svg)](https://agentmods.dev/skills/cambridgetcg/agenttool/coordinate-agent-work-hermes)
Your own site
<a href="https://agentmods.dev/skills/cambridgetcg/agenttool/coordinate-agent-work-hermes"><img src="https://agentmods.dev/badge/skills/cambridgetcg/agenttool/coordinate-agent-work-hermes.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,415 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 $0.00072 $0.01415
Opus 5 $0.00036 $0.00707
Sonnet 5 $0.00014 $0.00283
Haiku 4.5 $0.00007 $0.00142

Measured 8d ago against content hash 0a6ad2c7be6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

coordinate-agent-work-hermes 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 8d 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/integrations/hermes/skills/coordinate-agent-work-hermes/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coordinate Agent Work from Hermes

Use AgentTool Collab as a shared local journal. Keep Hermes responsible for its own agents and Kanban work. Do not mirror every operation between the systems or treat either one as automatic authority for the other.

Choose the plane explicitly

Prefer the credential-bound plane for resumable work, persisted cursors, reports, review, recovery, and session-fenced task attribution:

  • mcp_agenttool_collab_session_start
  • mcp_agenttool_collab_session_end
  • mcp_agenttool_collab_next and mcp_agenttool_collab_cursor_ack
  • credential-bound task, report, review, artifact, and handoff tools

Use the public presence plane only for optional discovery, routing hints, or v0.2 compatibility:

  • mcp_agenttool_collab_session_join
  • mcp_agenttool_collab_session_list
  • mcp_agenttool_collab_session_heartbeat
  • mcp_agenttool_collab_session_leave

Presence labels, capabilities, and live/stale state are self-declared. They do not authenticate a person, model, provider, account, health, competence, or permission. The planes do not become one identity merely because they share a label or workspace.

Run credential-bound coordination

  1. Confirm that every participating MCP process selects the same AGENTOOL_COLLAB_DB, and register the Hermes MCP server under the exact name agenttool.
  2. Call mcp_agenttool_collab_session_start with the repository root and an actor label. It opens the workspace, creates a local bearer, writes it to a mode-0600 host file, and binds this MCP process. Retain the returned workspace and session IDs, but never read the credential file or request its token or absolute path through model-facing tools.
  3. Call mcp_agenttool_collab_next at the start of a turn, after local work, and before relying on shared state. Omit event_limit for the 10-event MCP default or set an integer from 1 through 50. Process one page, call mcp_agenttool_collab_cursor_ack with its exact terminal next_anchor, then poll again if has_more is true. known_cursor validates an anchor but does not paginate or acknowledge. The limit bounds events and routed reports, not snapshot-head task, conflict, or handoff projections. Treat acknowledgement as processed, not agreed or accepted.
  4. Create bounded work, then call mcp_agenttool_collab_task_claim with the latest version before editing. Omit legacy actor arguments in the bound process; the server derives its coordination actor from the credential.
  5. Attach scoped references, append evidence with mcp_agenttool_collab_report_append, and report completion. Require a distinct bound session to inspect the evidence and call mcp_agenttool_collab_task_review for edit-task acceptance.
  6. Offer continuation with mcp_agenttool_collab_handoff_offer; transfer the advisory lease only after the exact recipient accepts. Resolve live leases, then call mcp_agenttool_collab_session_end when the host knows this session will not resume.

Read the full file on GitHub · 117 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. 8d ago First seen · 117 lines · 72 tokens per session scan A 0a6ad2c7be6d

Subscribe to this mod's changes

coordinate-agent-work-hermes is a skill published in the GitHub repository cambridgetcg/agenttool (0 stars, last pushed today), licensed Apache-2.0. It adds 72 tokens to every session and 1,415 once invoked, about $0.0004 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

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

optimize-a-query

Diagnose and fix a slow Postgres query in the builders-stack — read its EXPLAIN plan, find the missing index or the ORM N+1, and confirm the fix. Use when a page or endpoint is slow, a query times out, or pgstatstatements shows a hot query. Pairs with design-a-schema for the index itself.

lonormaly/builders-stack · 77 tokens

create-a-worktree

Create, inspect, or retire an isolated Builders Stack agent runtime through Worktree Zero. Use whenever parallel work needs another checkout or an old worktree needs cleanup.

lonormaly/builders-stack · 37 tokens