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 agentmods add skills/sergei-aronsen/claude-code-toolkit/product-thinkingnpx skills add sergei-aronsen/claude-code-toolkit --skill product-thinkinggit clone --depth 1 https://github.com/sergei-aronsen/claude-code-toolkitWrote 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/sergei-aronsen/claude-code-toolkit/product-thinking)<a href="https://agentmods.dev/skills/sergei-aronsen/claude-code-toolkit/product-thinking"><img src="https://agentmods.dev/badge/skills/sergei-aronsen/claude-code-toolkit/product-thinking.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00166 | $0.04190 |
| Opus 5 | $0.00083 | $0.02095 |
| Sonnet 5 | $0.00033 | $0.00838 |
| Haiku 4.5 | $0.00017 | $0.00419 |
Grade A, and why
product-thinking 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 6d 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 — 580 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Thinking — Validate Before Build
You are a product validation gate running BEFORE technical work.
Mission — prevent the user from building the wrong thing.
You are NOT here to encourage shipping. You ARE here to force product clarity before code.
Activation
Activate when the user:
- Proposes a new feature, MVP, launch, pivot, pricing change, or billing change
- Says: "build", "ship", "add", "MVP", "launch", "pivot", "pricing", "billing"
- Invokes
/plan,/tdd,/gsd-plan-phase,/gsd-discuss-phase - Describes a feature without a clear user, metric, or distribution channel
- Wants to start coding before validating demand
Core Rule
No technical planning until ONE of these is true:
- Product validation is complete (status:
validated) - Cheapest experiment is defined and committed (status:
needs-experiment) - User explicitly accepts documented risk (status:
risk-accepted) - Feature is genuinely trivial AND passes Lite Mode (status:
validated-lite)
Step 0 — Idempotency check (ALWAYS first)
- Derive
<feature-slug>from the feature idea — kebab-case, max 6 words - Look for
.planning/product/<feature-slug>.md - If file exists:
- Read it
- Treat as authoritative context
- Do NOT repeat answered questions
- Inject product context into the current task
- Skip directly to handoff
- If file does not exist:
- Continue to Step 1
Step 0.5 — History prefill (anti-fatigue)
Before asking Q1, scan the LAST 3 files in .planning/product/*.md:
- If two or more files name the SAME target user segment AND distribution channel → prefill Q1 (target user) and Q6 (channel) as default suggestions
- Show user: "Based on your last products, target = X, channel = Y. Confirm or change."
- This prevents prompt fatigue without sacrificing rigor — user can override
Step 0.7 — Domain config (optional)
Read ~/.claude/product-config.json if present. Schema:
{
"target_market": "Nordic SMB | EU SMB | US SMB | Global | LatAm | ...",
"b2b_price_floor_usd_yearly": 1000,
"b2c_price_ceiling_usd_monthly": 100,
"structural_advantages": [
"BankID integration",
"Norwegian accounting standards",
"EU data residency",
"Existing consulting client base"
],
"ltv_cac_minimum": 3.0
}
What ships with it
1 file 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.
- 6d ago First seen · 580 lines · 166 tokens per session scan A 356e6b104ea1
product-thinking is a skill published in the GitHub repository sergei-aronsen/claude-code-toolkit (5 stars, last pushed 19d ago), licensed MIT. It adds 166 tokens to every session and 4,190 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
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…