pm-data

A product-data analysis workflow for answering one specific question with PostHog or Amplitude, tools that record how people use a product. It writes the findings to a project wiki page.

In plain words
What is it for?
Use it to study trends, funnels, retention, and user paths, then record the result for product reviews or requirements documents.
Why use it?
It turns usage data into evidence for product decisions instead of relying only on opinions or observations.

Skill for Claude CodeCodex

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 skills/nmrtn/nanopm/pm-data
Any agent
npx skills add nmrtn/nanopm --skill pm-data
Clone the repo
git clone --depth 1 https://github.com/nmrtn/nanopm

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,319 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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.

ModelPer sessionOnce invoked
Fable 5 $0.00062 $0.03319
Opus 5 $0.00031 $0.01659
Sonnet 5 $0.00012 $0.00664
Haiku 4.5 $0.00006 $0.00332

Measured 2d ago against content hash 90824f2b2bab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

pm-data scanned grade C with 2 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 2d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

{ echo "ERROR: nanopm not installed. Run: curl -fsSL https://raw.githubusercontent.com/nmrtn/nanopm/main/setup | bash"; exit 1; }

Makes network callslowCapability

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

{ echo "ERROR: nanopm not installed. Run: curl -fsSL https://raw.githubusercontent.com/nmrtn/nanopm/main/setup | bash"; exit 1; }
pm-data/SKILL.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-host portability rules. When invoking AskUserQuestion:

  1. The header field MUST be a short noun phrase (≤ 12 characters). Mistral Vibe rejects longer headers with string_too_long. Pick from: Start, Target, Scope, Audience, Methodology, Feature, Question.
  2. The options list MUST have at least 2 items. Vibe rejects empty/single-option calls. For free-text input, always provide ≥ 2 framing options (e.g. Yes, here's the input / Skip) — never call ask_user_question with options: [].

Preamble (run first)

source ~/.nanopm/lib/nanopm.sh 2>/dev/null || \
  source .nanopm/lib/nanopm.sh 2>/dev/null || \
  { echo "ERROR: nanopm not installed. Run: curl -fsSL https://raw.githubusercontent.com/nmrtn/nanopm/main/setup | bash"; exit 1; }
nanopm_preamble

When to run this

Run /pm-data when:

  • You have a specific question about user behavior ("why do users drop at step 3?")
  • You're about to run /pm-challenge-me and want quanti to back the qualitatif signal
  • You're writing a PRD and need to quantify the problem size
  • You want to check the impact of a shipped feature

One question per run. A vague question ("how is the product doing?") produces useless output. A specific question ("what is the Day 7 retention for users who completed onboarding vs those who didn't?") produces an insight.

Phase 0: Prior context

source ~/.nanopm/lib/nanopm.sh 2>/dev/null || source .nanopm/lib/nanopm.sh 2>/dev/null || true
nanopm_context_read pm-data
nanopm_context_read pm-data

Check for a prior wiki data page — if it exists, show a one-line summary of the last analysis and its date. Don't repeat the same analysis unless explicitly requested.

source ~/.nanopm/lib/nanopm.sh 2>/dev/null || source .nanopm/lib/nanopm.sh 2>/dev/null || true
[ -f "$(nanopm_wiki_doc_path data)" ] && echo "DATA_EXISTS" || echo "DATA_MISSING"

Pull the upstream grounding through the query primitive — one read-side call that synthesizes the relevant wiki pages, instead of bespoke per-doc reads (the recipe pattern: query → reasoning → ingest). The raw docs stay out of this run; you reason over the cited synthesis the query returns. Print the prompt and dispatch it with the Agent tool (one subagent); on a host with no Agent tool, follow its steps inline.

Read the full file on GitHub · 268 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. 2d ago First seen · 268 lines · 62 tokens per session scan C 90824f2b2bab

Subscribe to this mod's changes

pm-data is a skill published in the GitHub repository nmrtn/nanopm (47 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 3,319 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens