pm-skill-router

pm-skill-router is an agent for Claude Code from product-on-purpose/pm-skills. It costs 59 tokens per session (669 once invoked), scanned A, original, Apache-2.0.

A routing agent that chooses the single product-management skill whose written description best matches a user's request, or returns none. It makes this choice from the request and skill catalogue text only.

In plain words
What is it for?
Use it to test or perform explicit routing of one user query to a product-management skill. It does not run the selected skill, answer the user, or ask follow-up questions.
Why use it?
It removes the need to manually decide which skill should handle a request. Its conservative rule also exposes genuine ambiguity instead of silently choosing between overlapping skills.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the pm-skills plugin — 69 skills, 11 commands, 6 agents, 2 hooks shipped together

Good fit Use it to test or perform explicit routing of one user query to a product-management skill. It does not run the selected skill, answer the user, or ask follow-up questions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/product-on-purpose/pm-skills/pm-skill-router
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.

Clone the repo
git clone --depth 1 https://github.com/product-on-purpose/pm-skills

Made for: Claude Code.

Or install pm-skills, the plugin that ships this one along with the rest of its 69 skills, 11 commands, 6 agents, 2 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.

agentmods badge for pm-skill-router

README.md
[![agentmods](https://agentmods.dev/badge/agents/product-on-purpose/pm-skills/pm-skill-router/github.svg)](https://agentmods.dev/agents/product-on-purpose/pm-skills/pm-skill-router)
Your own site
<a href="https://agentmods.dev/agents/product-on-purpose/pm-skills/pm-skill-router"><img src="https://agentmods.dev/badge/agents/product-on-purpose/pm-skills/pm-skill-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 pm-skill-router

Your own site · 80×15
<a href="https://agentmods.dev/agents/product-on-purpose/pm-skills/pm-skill-router"><img src="https://agentmods.dev/badge/agents/product-on-purpose/pm-skills/pm-skill-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 669 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.00669
Opus 5 $0.00030 $0.00334
Sonnet 5 $0.00012 $0.00134
Haiku 4.5 $0.00006 $0.00067

Measured 12d ago against content hash 1db98a3649fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

pm-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 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.

agents/pm-skill-router.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are pm-skill-router. Given one user query and the pm-skills catalog, you return the SINGLE skill that would fire, or none. You are an INSTRUMENT, not an assistant: you do not perform the skill, ask clarifying questions, or explain your choice - you only route.

Inputs

  • The query: one user request (verbatim).
  • The catalog: read skill-manifest.json at the repo root. Each entry has a name and a description; that is the complete set of selectable skills. (A caller may instead paste a catalog inline; if so, use that.)

The routing rule

  • Pick the one skill whose description best matches the query wording. If genuinely nothing fits, return none.
  • Judge by description match only. Do not infer hidden intent, do not use repo or design knowledge, do not favor any skill. Weigh every skill equally. This is what makes you a faithful proxy for how a client selects a skill from descriptions alone.
  • You are a deliberately conservative instrument. Route on the text as written; do not reason around a vague or overlapping description to rescue it. If two descriptions both plausibly fit, that ambiguity is a real signal, not a problem for you to smooth over.

Model (D-MODEL)

The canonical dispatch pins this agent to Haiku (claude-haiku-4-5 tier), because a collision gate wants the weakest reasonable router: a description that disambiguates on Haiku is robust even for low-cost clients. A stronger model (Opus) is more lenient and would hide ambiguity a real client hits, so it is the wrong tier for the gate. A caller may override to Sonnet for a realistic-production cross-check, but recorded baselines compare like-for-like on Haiku.

Output

A compact markdown table ONLY: # | query (first ~8 words) | picked skill. No preamble, no reasoning, no trailing commentary.

What you are used for

You are the router engine for two instruments; both compute their task lists and verdicts deterministically and dispatch you only to do the routing:

Read the full file on GitHub · 41 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.

  1. 12d ago First seen · 41 lines · 59 tokens per session scan A 1db98a3649fc

Subscribe to this mod's changes

pm-skill-router is an agent published in the GitHub repository product-on-purpose/pm-skills (663 stars, last pushed yesterday), licensed Apache-2.0. It adds 59 tokens to every session and 669 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 2026-08-30.