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.
npx skills add cambridgetcg/agenttool --skill coordinate-agent-work-hermesgit clone --depth 1 https://github.com/cambridgetcg/agenttoolWrote 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.
[](https://agentmods.dev/skills/cambridgetcg/agenttool/coordinate-agent-work-hermes)<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>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 | $0.00072 | $0.01415 |
| Opus 5 | $0.00036 | $0.00707 |
| Sonnet 5 | $0.00014 | $0.00283 |
| Haiku 4.5 | $0.00007 | $0.00142 |
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.
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_startmcp_agenttool_collab_session_endmcp_agenttool_collab_nextandmcp_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_joinmcp_agenttool_collab_session_listmcp_agenttool_collab_session_heartbeatmcp_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
- Confirm that every participating MCP process selects the same
AGENTOOL_COLLAB_DB, and register the Hermes MCP server under the exact nameagenttool. - Call
mcp_agenttool_collab_session_startwith the repository root and an actor label. It opens the workspace, creates a local bearer, writes it to a mode-0600host 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. - Call
mcp_agenttool_collab_nextat the start of a turn, after local work, and before relying on shared state. Omitevent_limitfor the 10-event MCP default or set an integer from 1 through 50. Process one page, callmcp_agenttool_collab_cursor_ackwith its exact terminalnext_anchor, then poll again ifhas_moreis true.known_cursorvalidates 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. - Create bounded work, then call
mcp_agenttool_collab_task_claimwith the latest version before editing. Omit legacy actor arguments in the bound process; the server derives its coordination actor from the credential. - Attach scoped references, append evidence with
mcp_agenttool_collab_report_append, and report completion. Require a distinct bound session to inspect the evidence and callmcp_agenttool_collab_task_reviewfor edit-task acceptance. - Offer continuation with
mcp_agenttool_collab_handoff_offer; transfer the advisory lease only after the exact recipient accepts. Resolve live leases, then callmcp_agenttool_collab_session_endwhen the host knows this session will not resume.
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.
- 8d ago First seen · 117 lines · 72 tokens per session scan A 0a6ad2c7be6d
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.
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.
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…
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…
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…
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.
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.