agentmods.dev

agent-task-router

agent-task-router is a skill for Claude Code, Codex from shannhk/hermes-agent-control-room. It costs 35 tokens per session (247 once invoked), scanned A, original, MIT.

A routing guide for an orchestrator that sends work to specialist Hermes agents through a shared task system.

In plain words
What is it for?
It is for writing task briefs, choosing specialists, checking their response folders, and combining delegated results.
Why use it?
It helps split larger requests into focused tasks and keep track of the specialists’ results.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 734repo +2 5mo ago A scan SkillSpector: pass 35 tokens original MIT

Good fit It is for writing task briefs, choosing specialists, checking their response folders, and combining delegated results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shannhk/hermes-agent-control-room/agent-task-router
View source ↗ shannhk/hermes-agent-control-room
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 shannhk/hermes-agent-control-room --skill agent-task-router
Clone the repo
git clone --depth 1 https://github.com/shannhk/hermes-agent-control-room

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 agent-task-router

README.md
[![agentmods](https://agentmods.dev/badge/skills/shannhk/hermes-agent-control-room/agent-task-router/github.svg)](https://agentmods.dev/skills/shannhk/hermes-agent-control-room/agent-task-router)
Your own site
<a href="https://agentmods.dev/skills/shannhk/hermes-agent-control-room/agent-task-router"><img src="https://agentmods.dev/badge/skills/shannhk/hermes-agent-control-room/agent-task-router/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 agent-task-router

Your own site · 80×15
<a href="https://agentmods.dev/skills/shannhk/hermes-agent-control-room/agent-task-router"><img src="https://agentmods.dev/badge/skills/shannhk/hermes-agent-control-room/agent-task-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 247 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00035 $0.00247
Opus 5.5 $0.00014 $0.00099
Sonnet 5.5 $0.00007 $0.00049
Haiku 4.5 $0.00003 $0.00025

Measured 2mo ago against content hash 9bbc384a78c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-task-router 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/agent-task-router/SKILL.md · 44 lines

What it actually says

Agent Task Router

Use this skill from an orchestrator agent.

The orchestrator routes work to specialists through /srv/agent-bus or another configured task bus.

Routing Flow

  1. Parse the user's request.
  2. Decide whether to answer directly or delegate.
  3. Pick the correct specialist from the registry.
  4. Write a clear task file to the specialist inbox.
  5. Include context, constraints, expected output, and approval gates.
  6. Track the task ID.
  7. Read the specialist result from outbox.
  8. Synthesize the final answer.
  9. Archive completed task files.

Task Quality Bar

A delegated task must include:

  • clear objective
  • relevant context
  • paths or links
  • constraints
  • what not to do
  • expected output
  • approval requirements

Routing Examples

SEO audit -> hermes-seo
Code bug -> hermes-dev
Campaign planning -> hermes-cmo
VPS health -> hermes-ops
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 · 44 lines · 35 tokens per session scan A 9bbc384a78c0

Subscribe to this mod's changes

agent-task-router is a skill published in the GitHub repository shannhk/hermes-agent-control-room (734 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 247 once invoked, about $0.0001 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.

Building agentsMulti-AgentProject managementagent-control-roomai-agentshermes-agentvps
Related

agent-task-router compared with skills from other repositories

agent-task-router next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agent-task-routershannhk/hermes-agent-control-roomSkill7345mo agoMITA35Claude Code, Codex
graph-engineering-workflowThanarak-q/graph-engineering-workflowSkill62mo agoMITA56Codex
slack-agent-meshnickvasilescu/slack-agent-meshSkill13mo agoMITA95Claude Code, Codex
council-opsKevin-the-minion/syndicate-osSkill52mo agoGPL-3.0A21Claude Code, Codex
evidence-based-verificationKevin-the-minion/syndicate-osSkill52mo agoGPL-3.0A25Claude Code, Codex
grounded-citationsKevin-the-minion/syndicate-osSkill52mo agoGPL-3.0A19Claude Code, Codex
federation-opsKevin-the-minion/syndicate-osSkill52mo agoGPL-3.0D22Claude Code, Codex