A first-pass task router that reads the user request and chooses whether to answer directly, run a built-in skill, dispatch a plugin worker, or ask for clarification.

It helps classify requests, build the small handoff message for a selected worker, and keep plugin and task state unchanged while routing.

It prevents the wrong tool from being selected when a request is unclear or matches more than one plugin.

router — 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

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/github.svg)](https://agentmods.dev/skills/cintia09/codenook/router)

Your own site

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

Your own site · 80×15

<a href="https://agentmods.dev/skills/cintia09/codenook/router"><img src="https://agentmods.dev/badge/skills/cintia09/codenook/router.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 542 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	$0.00542
Opus 5.5	$0.00000	$0.00217
Sonnet 5.5	$0.00000	$0.00108
Haiku 4.5	$0.00000	$0.00054

Measured 2mo ago against content hash ffe9f6fd2ed7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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.

The scan reads SKILL.md. This mod also ships 2 executable files (_bootstrap.py, bootstrap.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/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

router (builtin skill — self-bootstrap loader)

Role

The first sub-agent dispatched by the main session on every user turn that isn't pure chit-chat. It self-bootstraps from a fresh context by reading its own profile + the main-session contract + the workspace state. (Historically it then handed off to router-triage, which has been removed in M8.7; the conversational router-agent skill is the current decision engine.)

CLI

bootstrap.sh --user-input "<text>" [--workspace <dir>] [--task <T-NNN>] [--json]

--user-input — required; the verbatim user utterance the router must triage. Truncated downstream by router-dispatch-build.
--workspace — defaults to $CODENOOK_WORKSPACE then upward search for .codenook/.
--task — optional active task id; surfaced verbatim in the envelope even if no tasks/<id>/state.json exists yet.
--json — currently the only output mode.

Files read (in order)

<core>/agents/router.md — own profile (must exist)
<core>/core/shell.md — main session contract (must exist)
<ws>/.codenook/state.json — installed plugins + active tasks
<ws>/.codenook/plugins/<id>/plugin.yaml — for each installed plugin
config-resolve --plugin __router__ — resolves model preference (tier_strong per decision #44)

CN_CORE_ROOT env var overrides the core directory location (used by tests; defaults to the package root containing this skill).

Exit codes

code	meaning
0	bootstrapped, ready (envelope on stdout)
1	bootstrap failure (missing profile/shell/state)
2	usage error

Output schema

{
  "role": "router",
  "context": {
    "active_tasks":      ["T-001", ...],
    "active_task":       "T-007",   // null if --task not passed
    "installed_plugins": [{"id": "...", "version": "...",
                           "intent_patterns": [...], "_error": "..."?}],
    "model":             "opus-4.7"
  },
  "ready": true
}

Read the full file on GitHub · 61 lines

Files

What ships with it

2 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 · 61 lines · 0 tokens per session scan A ffe9f6fd2ed7

Subscribe to this mod's changes

router 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 542 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 next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
routercintia09/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