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.
npx skills add mshadmanrahman/pm-pilot --skill product-discoverygit clone --depth 1 https://github.com/mshadmanrahman/pm-pilotWrote 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.
[](https://agentmods.dev/skills/mshadmanrahman/pm-pilot/product-discovery)<a href="https://agentmods.dev/skills/mshadmanrahman/pm-pilot/product-discovery"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/product-discovery/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.
<a href="https://agentmods.dev/skills/mshadmanrahman/pm-pilot/product-discovery"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/product-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00107 | $0.03776 |
| Opus 5 | $0.00053 | $0.01888 |
| Sonnet 5 | $0.00021 | $0.00755 |
| Haiku 4.5 | $0.00011 | $0.00378 |
Grade A, and why
product-discovery 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.
discovery.md
Your product discovery copilot. Frame problems, plan research, synthesize insights, and package evidence -- without needing a UX researcher on your team.
How It Works
This skill runs as an interactive conversation. You talk, I guide. Every mode produces a real markdown artifact you can share with your team.
Four modes:
| Command | What it does | Output |
|---|---|---|
/product-discovery |
Start a new discovery cycle | discovery/{name}/brief.md |
/product-discovery interview |
Generate an interview guide | discovery/{name}/interview-guide.md |
/product-discovery synthesize |
Turn raw notes into patterns | discovery/{name}/synthesis.md |
/product-discovery package |
Create a stakeholder one-pager | discovery/{name}/one-pager.md |
You can run them in sequence (full cycle) or individually (just need an interview guide? go).
Mode 1: Start a Discovery Cycle
Purpose
Frame what you're investigating, who's affected, and what success looks like. This is the foundation everything else builds on.
Entry
When the user invokes /product-discovery (no arguments), begin this mode.
Interaction Flow
Step 1: The Dump
Start with:
"Before we structure anything -- what's the messy thinking? What problem are you circling? Who's struggling? What made you think 'we should look into this'? Just dump it. Rough is fine."
Wait for the user's response. This is critical. Do not skip to structure.
Step 2: Reflect Back the Core Tension
After the dump, reflect back:
- The core problem you heard (one sentence)
- Who seems most affected
- The hidden assumption they might not have said out loud
- Any tension or contradiction in what they described
Ask: "Did I get that right? What did I miss?"
Step 3: Problem Hypothesis (Guided)
Walk through these one question at a time. Do NOT present them all at once.
- Who specifically is struggling?
- Push for specificity. "Users" is not a persona. "Mid-market SaaS PMs with no dedicated researcher" is.
- If they're vague, offer 2-3 persona options based on what they dumped.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 403 lines · 107 tokens per session scan A 5329e77a0750
product-discovery is a skill published in the GitHub repository mshadmanrahman/pm-pilot (20 stars, last pushed 5d ago), licensed MIT. It adds 107 tokens to every session and 3,776 once invoked, about $0.0005 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.
Other skills, from other repositories
analyze-codebase
Run comprehensive PLG analysis on a codebase to detect tech stack, existing growth features, and revenue opportunities. Use when the user says "analyze", "scan", "audit codebase", or "find growth opportunities".
build-implementation
Generate context-aware implementation prompts for a selected growth loop. Use when the user says "build", "implement", "generate code", "create prompt", or "how do I build this".
deploy-telemetry
Set up analytics and tracking infrastructure for growth loops. Use when the user says "deploy telemetry", "set up analytics", "tracking", "events", "push to supabase", or "skene push".
plan-growth-loop
Generate prioritized growth loops with implementation roadmaps based on codebase analysis. Use when the user says "plan", "growth loops", "prioritize", "what should I build", or "roadmap".
validate-loop
Check if growth loop requirements are actually implemented in the codebase. Use when the user says "validate", "check status", "skene status", "is it done", or "verify implementation".
initialize-config
Set up Skene configuration for a project. Use when starting a new PLG analysis, when .skene.config is missing, or when the user says "skene init", "set up skene", or "configure skene".