What is router-agent?

A task-creation entry point that prepares the context for a separate worker agent. It creates task files, renders the worker's instructions, and, after confirmation, starts the first orchestration step.

Use it once per user turn to create a task, prepare its prompt and state, request confirmation when needed, and launch the first worker step.

It separates deterministic task setup from the worker that performs the actual conversational task.

router-agent — Skill for Claude Code and Codex by cintia09/CodeNook

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 cintia09/CodeNook --skill router-agent

Clone the repo

git clone --depth 1 https://github.com/cintia09/CodeNook

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cintia09/codenook/router-agent/github.svg)](https://agentmods.dev/skills/cintia09/codenook/router-agent)

Your own site

<a href="https://agentmods.dev/skills/cintia09/codenook/router-agent"><img src="https://agentmods.dev/badge/skills/cintia09/codenook/router-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cintia09/codenook/router-agent"><img src="https://agentmods.dev/badge/skills/cintia09/codenook/router-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,282 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.01282
Opus 5.5	$0.00000	$0.00513
Sonnet 5.5	$0.00000	$0.00256
Haiku 4.5	$0.00000	$0.00128

Measured 2mo ago against content hash 00346e0618c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

router-agent 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.

The scan reads SKILL.md. This mod also ships 2 executable files (render_prompt.py, spawn.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/codenook-core/skills/builtin/router-agent/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

router-agent (builtin skill — M8.2)

Role

Per-turn entry point the main session calls to dispatch a real subagent for conversational task creation. The router-agent is the SOLE domain-aware component on the task-creation side (see docs/router-agent.md §2).

This skill ships:

File	Purpose
`spawn.sh`	CLI entry the main session invokes once per user turn. Thin shell wrapper around `render_prompt.py`.
`render_prompt.py`	Deterministic context-prep + handoff helper. Acquires the per-task fcntl lock, mutates `tasks/<tid>/`, renders the system prompt, and on `--confirm` materialises `state.json` and runs the first `orchestrator-tick`.
`prompt.md`	Long-form system-prompt template for the spawned subagent.
`schemas/`	M5 YAML DSL schemas for the four canonical files (shipped in M8.1).

Layering reminder

spawn.sh does not call an LLM. Its job is the deterministic context-prep + handoff envelope: it writes a fully-rendered prompt to tasks/<tid>/.router-prompt.md and emits a JSON envelope that tells the main session "go spawn a Task subagent with this prompt". The subagent itself writes back to router-context.md / router-reply.md / draft-config.yaml; the next spawn.sh invocation observes the new state.

This split keeps spawn.sh portable across host runtimes (Claude Code Task tool, Copilot CLI task tool, plain shell) while pinning all domain logic inside the subagent prompt.

Inputs

Flag	Required	Meaning
`--task-id <T-NNN>`	yes	Task id to operate on (creates `tasks/<tid>/` if absent).
`--workspace <path>`	yes	Workspace root. Tasks live under `<ws>/.codenook/tasks/`, plugins under `<ws>/.codenook/plugins/`.
`--user-turn <text>`	no	The user's latest utterance (omit on initial spawn before any user input).
`--user-turn-file <path>`	no	Same as `--user-turn` but read from a file (avoids shell-quoting hazards).
`--confirm`	no	Handoff mode: validate the current `draft-config.yaml`, materialise `state.json`, and run the first `orchestrator-tick`.

Read the full file on GitHub · 103 lines

Files

What ships with it

7 files 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.

2mo ago First seen · 103 lines · 0 tokens per session scan A 00346e0618c5

Subscribe to this mod's changes

router-agent is a skill published in the GitHub repository cintia09/CodeNook (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,282 tokens. 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.

Building agents

router-agent next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
router-agentcintia09/CodeNook	Skill	5	1mo ago	MIT	A	0	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	2d ago	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	2d ago	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	yesterday	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	315k	5d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code