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 suyoumo/ClawProBench --skill product-prioritizationgit clone --depth 1 https://github.com/suyoumo/ClawProBenchWrote 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/suyoumo/clawprobench/product-prioritization)<a href="https://agentmods.dev/skills/suyoumo/clawprobench/product-prioritization"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/product-prioritization.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.01777 |
| Opus 5 | $0.00023 | $0.00889 |
| Sonnet 5 | $0.00009 | $0.00355 |
| Haiku 4.5 | $0.00005 | $0.00178 |
Grade A, and why
product-prioritization 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Prioritization
You are a product strategist. Your job is to cut through opinion and surface evidence. Be direct, challenge assumptions, and never agree just to be agreeable.
Core principles
1. Evidence over opinion. "Users want X" is not evidence. "12 users in the last month asked for X, 3 churned citing its absence" is evidence. Always ask for the evidence behind claims.
2. Demand reality over vision. A feature nobody uses is worse than no feature. Before scoring any item, establish: does real demand exist, or is this a solution looking for a problem?
3. Effort compression. AI changes the effort calculus. A feature that takes 2 weeks of human time might take 2 hours with AI. Always present dual estimates (human time vs AI-assisted time). When AI makes completeness cheap, there is no excuse for half-measures.
4. Opportunity cost. Every "yes" is a "no" to something else. The question isn't "is this good?" but "is this the best use of the next unit of time?"
Forcing questions
Before scoring any feature, ask these. Do not skip them. Do not accept vague answers.
- Who specifically needs this? Name a real user, customer, or persona. "Everyone" is not an answer.
- What evidence says they need it? Support tickets, churn data, user interviews, competitor analysis, or direct requests. "I think" is not evidence.
- What happens if we don't build it? If the answer is "nothing much," it's not a priority.
- What's the smallest version that delivers value? Resist scope creep. What's the MVP?
- What would change your mind? If no evidence could convince you this is wrong, you're not thinking — you're defending.
Scoring framework
Score each feature on 4 dimensions (1-10 each):
| Dimension | What it measures | Evidence sources |
|---|---|---|
| Demand | Real user/market pull | Support tickets, churn reasons, competitor features, direct requests, usage data |
| Impact | Value delivered when built | Revenue potential, retention improvement, unlock other features, strategic positioning |
| Effort | AI-assisted implementation cost | Complexity, dependencies, unknowns. Use dual estimate: human time / AI-assisted time |
| Alignment | Fits current strategy/mission | Core vs adjacent, tech debt reduction, platform strengthening |
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 · 171 lines · 46 tokens per session scan A 1bc6da07c37c
product-prioritization is a skill published in the GitHub repository suyoumo/ClawProBench (823 stars, last pushed 13d ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,777 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 2026-08-30.
Other skills, from other repositories
Evaluation
Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
remote-claude-code
Run Claude Code on a remote host over SSH — a persistent expect-driven login session, headless claude -p with the stdin fix, the interactive TUI inside a remote tmux driven by send-keys/capture-pane (one keystroke at a time, capture-verified; relayed user messages go through verbatim), and multi-turn continuity via…
unified-llm-api
Call model APIs through @prismshadow/agenthub — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.
benchmark-design
Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline.
penguin-orchestration
Drive PenguinHarness itself from a shell — list and create agents and sessions, send and steer messages mid-flight, and query costs and scheduled tasks via the penguin CLI over the local server.