pm-productboard-insights

pm-productboard-insights is a skill for Claude Code from marfoerst/the-pragmatic-pm. It costs 141 tokens per session (2,883 once invoked), scanned A, original, MIT.

A transcript-to-Productboard workflow that turns customer conversations into atomic Insights: specific needs or problems preserved in the customer's own words. Productboard is a product-management tool for collecting and organizing customer feedback.

In plain words
What is it for?
Use it to extract attributed customer quotes from transcripts and submit them as Productboard Notes, with links to features when the official specification supports them.
Why use it?
It removes the need to manually find, separate, and file customer demands from sales calls, interviews, or support sessions. It also keeps evidence distinct from a product team's interpretation.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pm-toolkit plugin — 54 skills, 5 agents, 4 hooks shipped together

Good fit Use it to extract attributed customer quotes from transcripts and submit them as Productboard Notes, with links to features when the official specification supports them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marfoerst/the-pragmatic-pm/pm-productboard-insights
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 marfoerst/the-pragmatic-pm --skill pm-productboard-insights
Clone the repo
git clone --depth 1 https://github.com/marfoerst/the-pragmatic-pm

Made for: Claude Code.

Or install pm-toolkit, the plugin that ships this one along with the rest of its 54 skills, 5 agents, 4 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-productboard-insights

README.md
[![agentmods](https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-productboard-insights/github.svg)](https://agentmods.dev/skills/marfoerst/the-pragmatic-pm/pm-productboard-insights)
Your own site
<a href="https://agentmods.dev/skills/marfoerst/the-pragmatic-pm/pm-productboard-insights"><img src="https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-productboard-insights/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-productboard-insights

Your own site · 80×15
<a href="https://agentmods.dev/skills/marfoerst/the-pragmatic-pm/pm-productboard-insights"><img src="https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-productboard-insights.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 141 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,883 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00141 $0.02883
Opus 5 $0.00071 $0.01442
Sonnet 5 $0.00028 $0.00577
Haiku 4.5 $0.00014 $0.00288

Measured 12d ago against content hash c850fa89ba81, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

pm-productboard-insights scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sS -X POST https://api.productboard.com/v2/notes \
skills/pm-productboard-insights/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Productboard Insights from Transcripts

You turn a raw transcript into structured customer Insights and file them in Productboard. Read domain-context.md at the plugin root for company, product, persona, compliance, and industry context, and read personal-context.md if available for the user's role and preferences. Adapt all outputs — product-area names, tags, terminology — to match that context.

Core Principle

An Insight is evidence, captured in the customer's own words — not your interpretation of it. One transcript yields many insights; each is atomic (one demand per insight), verbatim (the quote is preserved, not paraphrased away), and attributed (who said it, which customer/company). Your job is to lift the signal cleanly and file it where the product team will find it — not to decide the roadmap. Resist editorializing: "User wants bulk export" is weaker evidence than the quote that produced it.

A demand is anything the customer expresses a need, friction, desire, or constraint about — even when phrased as praise ("the one thing I'd never give up is...") or as a workaround ("so I just export to Excel and do it by hand"). Capture all of these.

Phase 0: Preflight — the Notes API (do this first, before extracting anything)

Critical: In Productboard, "Insights" are stored as Notes, and notes are created through the Notes APIPOST https://api.productboard.com/v2/notes with a Bearer token. The official Productboard MCP (https://mcp.productboard.com) is spec-centric (search/read/edit specs, comment, update status) and cannot create insights; use it only, and optionally, to resolve which feature an insight should link to.

This skill writes via the Notes API + token. Preflight:

  1. Get the token. Read it from the PRODUCTBOARD_API_TOKEN environment variable. If it's not set, ask the user to provide it (a Productboard public API token) and to export it for the session — export PRODUCTBOARD_API_TOKEN=…. Never paste, echo, log, or hardcode the token into files or commands; reference it only as $PRODUCTBOARD_API_TOKEN.
  2. Verify access with a cheap read — GET https://api.productboard.com/v2/notes?pageLimit=1 with the Authorization: Bearer $PRODUCTBOARD_API_TOKEN and X-Version: 1 headers. A 200 confirms the token and the workspace it belongs to. On 401, stop and ask for a valid token before going further.
  3. If a token can't be obtained, fall back to draft-only: produce the structured insights for manual paste and say clearly that nothing was filed.
  4. (Optional) feature linking. If the official spec MCP is connected, you may search specs to resolve link targets — reads only during preflight, create/modify nothing.

Read the full file on GitHub · 167 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 · 167 lines · 141 tokens per session scan A c850fa89ba81

Subscribe to this mod's changes

pm-productboard-insights is a skill published in the GitHub repository marfoerst/the-pragmatic-pm (8 stars, last pushed 2mo ago), licensed MIT. It adds 141 tokens to every session and 2,883 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.