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 shannhk/hermes-agent-control-room --skill agent-registry-managergit clone --depth 1 https://github.com/shannhk/hermes-agent-control-roomWrote 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/shannhk/hermes-agent-control-room/agent-registry-manager)<a href="https://agentmods.dev/skills/shannhk/hermes-agent-control-room/agent-registry-manager"><img src="https://agentmods.dev/badge/skills/shannhk/hermes-agent-control-room/agent-registry-manager/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.
<a href="https://agentmods.dev/skills/shannhk/hermes-agent-control-room/agent-registry-manager"><img src="https://agentmods.dev/badge/skills/shannhk/hermes-agent-control-room/agent-registry-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.00132 |
| Opus 5 | $0.00013 | $0.00066 |
| Sonnet 5 | $0.00005 | $0.00026 |
| Haiku 4.5 | $0.00003 | $0.00013 |
Grade A, and why
agent-registry-manager 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 12d 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.
What it actually says
Agent Registry Manager
Maintain the registry that tells the orchestrator which agents exist and what they do.
Default registry path:
/srv/agent-bus/registry/agents.yaml
Each registry entry should include:
- agent name
- role
- docs path
- data dir
- task queue
- gateway URL if used
- dashboard URL if used
- allowed work
- forbidden work
- credential notes without values
Do not store secrets in the registry.
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.
- 12d ago First seen · 30 lines · 25 tokens per session scan A 41e2812924c3
agent-registry-manager is a skill published in the GitHub repository shannhk/hermes-agent-control-room (709 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 132 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
graph-engineering-workflow
Plan and verify bounded agent graphs for complex coding work. Use when a coding agent needs to coordinate independent implementation, research, verification, auditing, isolated writers, merge ownership, or targeted repair loops. Prefer a single loop for small or genuinely sequential tasks.
slack-agent-mesh
Connect an existing agent (Hermes, Claude Code, Codex, any stdin/stdout CLI, an HTTP endpoint, or an MCP client) to Slack Agent Mesh, and operate correctly inside it — addressing agents by @name, delegating agent-to-agent, and respecting loop limits and untrusted-content rules. Use when wiring an agent into a shared…
council-ops
Use when running or participating in a council audit (altered-frame review).
evidence-based-verification
Use when a claim, fix, or audit finding needs proof — verify with byte-level evidence.
grounded-citations
Use when answering with sources — every claim gets a verifiable citation.
federation-ops
Use when working the Syndicate OS board, tenders, or provenance graph.