triage-requests

triage-requests is a command for Claude Code from phuryn/pm-skills. It costs 15 tokens per session (1,034 once invoked), scanned A, original, MIT.

A tool for sorting and prioritizing many feature requests from customers or stakeholders. It can work with pasted text or uploaded files such as CSVs, spreadsheets, and text documents.

In plain words
What is it for?
Use it to review support requests, sales feedback, survey responses, or other proposed product changes.
Why use it?
It turns an unorganized list into a clearer backlog by extracting the underlying request, context, and signs of repeated demand. It also helps connect requests to product goals and constraints.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the pm-product-discovery plugin — 13 skills, 5 commands shipped together

Good fit Use it to review support requests, sales feedback, survey responses, or other proposed product changes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/phuryn/pm-skills/triage-requests
About the project

phuryn/pm-skills is a marketplace of reusable skills, commands, and plugins that guide AI assistants through product-management work such as discovery, strategy, planning, metrics, launches, and growth. It is for product managers and teams using Claude Code, Cowork, or compatible assistants. The catalogue entries are the project's own workflows and extensions.

phuryn/pm-skills · 26,507 stars · on GitHub · productcompass.pm

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/phuryn/pm-skills

Made for: Claude Code.

Or install pm-product-discovery, the plugin that ships this one along with the rest of its 13 skills, 5 commands.

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 triage-requests

README.md
[![agentmods](https://agentmods.dev/badge/commands/phuryn/pm-skills/triage-requests/github.svg)](https://agentmods.dev/commands/phuryn/pm-skills/triage-requests)
Your own site
<a href="https://agentmods.dev/commands/phuryn/pm-skills/triage-requests"><img src="https://agentmods.dev/badge/commands/phuryn/pm-skills/triage-requests/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 triage-requests

Your own site · 80×15
<a href="https://agentmods.dev/commands/phuryn/pm-skills/triage-requests"><img src="https://agentmods.dev/badge/commands/phuryn/pm-skills/triage-requests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,034 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 $0.00015 $0.01034
Opus 5 $0.00008 $0.00517
Sonnet 5 $0.00003 $0.00207
Haiku 4.5 $0.00002 $0.00103

Measured 7d ago against content hash 553e49802303, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-22, from the pricing page.

Security

Grade A, and why

triage-requests 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 7d 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.

pm-product-discovery/commands/triage-requests.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/triage-requests -- Feature Request Triage

Take a pile of feature requests — from support tickets, sales calls, surveys, or Slack — and turn them into a prioritized, actionable backlog.

Invocation

/triage-requests                           # asks for input
/triage-requests [paste a list of requests]
/triage-requests [upload a CSV/spreadsheet]

Workflow

Step 1: Accept Feature Requests

Accept requests in any format:

  • Pasted text: List of requests, one per line or paragraph
  • Uploaded file: CSV, Excel, or text file with request data
  • Structured data: If the input has columns (requester, request, date, etc.), preserve them

If no input is provided, ask the user to paste or upload their feature requests.

Parse each request to extract:

  • The core ask (what the user wants)
  • Context (who asked, when, why — if available)
  • Frequency signals (how many people asked for similar things)

Step 2: Gather Prioritization Context

Ask the user (conversationally, not all at once):

  • What is the product? What stage is it in?
  • What are the current strategic goals or OKRs? (helps assess alignment)
  • Any constraints to consider? (team size, technical debt, upcoming deadlines)
  • Are there segments whose requests should carry more weight? (enterprise, churning users, power users)

Step 3: Categorize and Analyze

Apply the analyze-feature-requests skill:

  • Theme clustering: Group similar requests into themes (e.g., "reporting & analytics", "collaboration", "mobile experience")
  • Request count per theme: How many unique requests map to each theme
  • Strategic alignment: Rate each theme against stated goals (High/Medium/Low/None)
  • Segment analysis: Which user segments are driving which themes
  • Sentiment signals: Are requests accompanied by frustration, churn threats, or delight?

Step 4: Prioritize

Apply the prioritize-features skill:

For each theme (and the top individual requests within each theme):

Factor Assessment
Impact How many users affected? How severely?
Strategic alignment Does it serve current goals?
Effort estimate T-shirt size (S/M/L/XL)
Risk What happens if we don't do this?
Revenue signal Is this tied to deals, retention, or expansion?

Read the full file on GitHub · 121 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. 7d ago First seen · 121 lines · 15 tokens per session scan A 553e49802303

Subscribe to this mod's changes

triage-requests is a command published in the GitHub repository phuryn/pm-skills (26,507 stars, last pushed 7d ago), licensed MIT. It adds 15 tokens to every session and 1,034 once invoked, about $0.0001 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 2026-09-15.