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 majiayu000/spellbook --skill product-discoverygit clone --depth 1 https://github.com/majiayu000/spellbookWrote 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/majiayu000/spellbook/product-discovery)<a href="https://agentmods.dev/skills/majiayu000/spellbook/product-discovery"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/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/majiayu000/spellbook/product-discovery"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/product-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00043 | $0.02940 |
| Opus 5 | $0.00022 | $0.01470 |
| Sonnet 5 | $0.00009 | $0.00588 |
| Haiku 4.5 | $0.00004 | $0.00294 |
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 8d 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 — 460 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Discovery
Core Principles
- Continuous Discovery — Weekly user conversations, not episodic research
- Outcome-Driven — Start with outcomes to achieve, not solutions to build
- Assumption Testing — Validate risky assumptions before committing resources
- Co-Creation — Build with customers, not just for them
- Data-Driven — Use evidence over intuition and stakeholder opinions
- Problem-First — Deeply understand the problem space before ideating solutions
Hard Rules (Must Follow)
These rules are mandatory. Violating them means the skill is not working correctly.
No Solution-First Thinking
Never start with a solution. Always define the problem and outcome first.
❌ FORBIDDEN:
"We should build a search bar for the product page"
"Let's add AI recommendations"
"Users need a mobile app"
✅ REQUIRED:
"Problem: Users can't find products (40% exit rate on catalog)
Outcome: Reduce exit rate to 20%
Possible solutions:
1. Search bar with filters
2. AI-powered recommendations
3. Better category navigation
4. Visual product browsing"
Evidence-Based Decisions
Never assume user needs without evidence from real user research.
❌ FORBIDDEN:
- "Users probably want X" (assumption without data)
- "Our competitor has X, so we need it too" (copycat without validation)
- "The CEO thinks we should build X" (HiPPO without evidence)
- "It's obvious users need X" (intuition without validation)
✅ REQUIRED:
- "5 out of 8 interviewed users mentioned X as a pain point"
- "Analytics show 60% of users abandon at step 3"
- "Prototype test: 7/10 users completed task successfully"
- "Survey (n=500): 45% rated feature as 'must have'"
Minimum Interview Threshold
Never validate a problem with fewer than 5 user interviews per segment.
❌ FORBIDDEN:
- "We talked to 2 users and they loved the idea"
- "One customer requested this feature"
- "Based on a quick chat with sales..."
✅ REQUIRED:
| Segment | Interviews | Key Finding |
|---------|------------|-------------|
| Power Users | 6 | 5/6 struggle with X |
| New Users | 5 | 4/5 drop off at onboarding |
| Churned | 5 | 3/5 cited missing feature Y |
Minimum per segment: 5 interviews
Confidence increases with more interviews
What ships with it
6 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.
- 8d ago First seen · 460 lines · 43 tokens per session scan A 3321ea4ae402
product-discovery is a skill published in the GitHub repository majiayu000/spellbook (278 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 2,940 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
pneuma-session
Instructions for renaming an active Pneuma session and replacing its default preview with a useful title and summary. A Pneuma session is one work area inside a larger project.
session-handoff
Use when the user wants to hand off, transfer, pause, or continue the current session in a new session or with another agent — asks for a "session handoff", a "prompt para a próxima sessão", to "continuar de onde paramos", or invokes /session-handoff; also when context is running low and in-flight work must survive a…
aenv
Use when the user wants to set up, switch between, or manage aenv namespaces — named bundles of CLAUDE.md, skills, MCP entries, and other AI-coding-harness config — in a project OR globally across $HOME. Triggers include aenv … mentioned directly, "switch namespace/profile", "activate/deactivate", "create/snapshot a…
cao-session-management
Interact with CAO (CLI Agent Orchestrator) — launch multi-agent sessions, check status, send follow-up instructions, unblock stuck terminals, or shut down sessions. Use when working with CAO sessions in any capacity.
mulmoterminal-keys
Bind keyboard shortcuts and fix keyboard/clipboard behaviour in MulmoTerminal. Writes keymap, which Settings cannot set at all — its Keyboard shortcuts section is read-only, listing every action bound or not plus a send row. Explains copyOnSelect, questionPaneEnabled and terminalSubmit, which have their own Settings…
tokf-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.