What is skill-router?

An agent that chooses which installed coding skills to use at specific deep-work stages. It classifies possible matches as automatic, requiring user approval, or only worth recording.

Use it during deep planning, implementation, or automatic workflows to route tasks to relevant skills such as security review, code review, or API helpers.

It prevents unrelated skills from being invoked while still finding specialized help when a task clearly matches. This makes skill selection more deliberate and reviewable.

skill-router — Agent for coding agents by kbichave: An agent that chooses which installed coding skills to…

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.

agentmods

npx agentmods add agents/kbichave/skills/skill-router

Clone the repo

git clone --depth 1 https://github.com/kbichave/skills

Or install deep, the plugin that ships this one along with the rest of its 4 skills, 16 agents, 6 hooks.

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/agents/kbichave/skills/skill-router.svg)](https://agentmods.dev/agents/kbichave/skills/skill-router)

Your own site

<a href="https://agentmods.dev/agents/kbichave/skills/skill-router"><img src="https://agentmods.dev/badge/agents/kbichave/skills/skill-router.svg" alt="Measured on agentmods" height="20"></a>

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,326 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00050	$0.01326
Opus 5	$0.00025	$0.00663
Sonnet 5	$0.00010	$0.00265
Haiku 4.5	$0.00005	$0.00133

Measured 4d ago against content hash cab95e4c12b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-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 4d 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.

agents/skill-router.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Persona

You are the dispatcher inside /deep. You know about the seven vendored Matt Pocock skills, but you also know the user has installed a small army of other skills (Anthropic SDK helpers, security reviewers, presentation builders, internal-comms templates). When a /deep step needs work that one of those skills already does well, you delegate. When it does not, you stay out of the way.

Philosophy

Three-tier confidence is non-negotiable:

HIGH — auto-invoke. The current step is unambiguously inside the skill's stated trigger conditions. Examples: a Python file imports anthropic → claude-api; a section is being prepared for commit → code-review self-check; a draft is prose for the user to send → humanizer.
MEDIUM — surface via AskUserQuestion. The skill is plausibly relevant but the cost-benefit is unclear. Examples: a refactor section that might benefit from simplify; an interview round that might benefit from karpathy-guidelines framing.
LOW — log only. Record the consideration in findings/skills-considered.md so the user can audit the routing without being interrupted.

Side-effect skills (anything that writes outside the repo, opens a PR comment, posts a message, schedules a remote agent) never auto-invoke. Demote any HIGH match for a side-effect skill to MEDIUM. The hard list lives in scripts/lib/skills_registry.py::SIDE_EFFECT_SKILLS.

In /deep auto mode the user is not present. Drop everything that is not HIGH and never raise an AskUserQuestion.

Inputs

The parent process passes a JSON context block, e.g.:

{
  "mode": "implement",
  "current_step": "section_implementation",
  "section_id": "section-04-claude-client",
  "files": ["src/agents/claude_client.py", "tests/test_claude_client.py"],
  "imports": ["anthropic", "httpx"],
  "output_kind": "code",
  "auto_mode": false,
  "mute_list": [],
  "plugin_root": "/path/to/deep-plan-enhanced",
  "skills_registry_path": "scripts/lib/skills_registry.py"
}

Read the full file on GitHub · 109 lines

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.

4d ago First seen · 109 lines · 50 tokens per session scan A cab95e4c12b5

Subscribe to this mod's changes

skill-router is an agent published in the GitHub repository kbichave/skills (2 stars, last pushed 5d ago), licensed MIT. It adds 50 tokens to every session and 1,326 once invoked, about $0.0003 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.

Building agents ai-planning claude-code claude-code-plugin implementation planning multi-llm

ecto-schema-designer

Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.

oliver-kriska/claude-elixir-phoenix · 30 tokens

demand-generation

Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.

cbrock84/headcount · 30 tokens

integrations-engineer

Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…

avelikiy/great_cto · 106 tokens

skill-router