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 shanmukhaditya/agent-skills --skill world-class-product-teamgit clone --depth 1 https://github.com/shanmukhaditya/agent-skillsWrote 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/shanmukhaditya/agent-skills/world-class-product-team)<a href="https://agentmods.dev/skills/shanmukhaditya/agent-skills/world-class-product-team"><img src="https://agentmods.dev/badge/skills/shanmukhaditya/agent-skills/world-class-product-team/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/shanmukhaditya/agent-skills/world-class-product-team"><img src="https://agentmods.dev/badge/skills/shanmukhaditya/agent-skills/world-class-product-team.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00110 | $0.02247 |
| Opus 5 | $0.00055 | $0.01123 |
| Sonnet 5 | $0.00022 | $0.00449 |
| Haiku 4.5 | $0.00011 | $0.00225 |
Grade A, and why
world-class-product-team 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 12d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
World-Class Product Team
Act as the chief product officer and final editor. Build a defensible understanding of the product, direct a reporting hierarchy, and turn evidence into decisions an implementation team can execute without guessing.
Non-negotiables
- Inspect before proposing. Treat the repository, running product, product documents, issue history, tests, analytics, support evidence, and user-provided material as the product record.
- Research current external facts on the day of the run. Record the exact research date and cite sources. Never present memory as current research.
- Separate observed fact, sourced fact, inference, hypothesis, and recommendation.
- Optimize for durable user and business outcomes, not feature volume or novelty.
- Default the selected portfolio to 70% new or materially improved product capabilities and 30% bug, reliability, performance, accessibility, and product-debt fixes, measured by estimated effort points.
- Override 70:30 only for a critical safety, security, data-loss, legal, or availability issue. Explain the temporary deviation and the path back to the target allocation.
- Reject vague advice. Every selected item must satisfy the relevant definition of ready in
references/deliverable-contract.md. - Preserve scope: analyze and specify unless the user also asks for implementation. Do not modify product source code during a product-planning run.
- Surface uncertainty. Do not invent users, metrics, analytics, incidents, competitor behavior, or technical facts.
Select the operating mode
Use Full Council when the user asks for a complete product understanding, a roadmap, a major improvement plan, or an open-ended assessment. Use all ten logical roles described in references/team-roster.md.
Use Focused Council for a bounded surface, workflow, feature, or incident. Keep the chief product officer, appoint the one relevant director, and use two to four relevant specialists. State which roles were used and why the smaller team is sufficient.
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.
- 12d ago First seen · 165 lines · 110 tokens per session scan A 52a1b3c701a4
world-class-product-team is a skill published in the GitHub repository shanmukhaditya/agent-skills (3 stars, last pushed 20d ago), licensed MIT. It adds 110 tokens to every session and 2,247 once invoked, about $0.0006 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
bmad-deep-recon
Decision-grade research, three ways: draft a deep-research prompt for the user to run in their own tool (ChatGPT, Gemini, Grok, Perplexity, …), process a finished research report — file it, distill a succinct cited summary with metadata that downstream skills consume without reprocessing — or run the research here…
hedgehog
Use when the user writes the word "Hedgehog" anywhere in a request, or has agreed to install the Hedgehog build discipline in a project that does not have it yet. Hedgehog builds prose as well as code — articles, essays, blog posts, tweets, threads, newsletters, announcements, and marketing or product copy of any…
conventional-commits
Use when uncommitted changes need to be split into atomic, conventional commits ordered for review. Triggers on "commit this", "make commits", "clean up commits", "commit the changes". In Hedgehog, each Loop step is already meant to be its own commit — this skill matters most when a Correction Protocol fast-forward…
pr-writing
Use whenever writing a PR title/description, a commit message body, a code review comment, or an issue — in Hedgehog's own repo or any consuming project. Triggers on "open a PR", "write the PR description", "comment on this PR", "file an issue". Covers writing style (terse, info-dense, Simplified Technical English)…
hedgehog-daily
Use when a change request lands on a project that already has .hedgehog/ and no build in flight — a finished build being adjusted, or an adopted repo's next piece of work. Triggers on any "change this", "fix this", "add this" on such a project. Sizes the request against the installed core's own layers and routes it to…
hedgehog-writing-gate
Use when the user asks to write, draft, or edit a standalone piece of prose — an article, essay, blog post, tweet, thread, newsletter, announcement, email, pitch, or other copy — and the request does not already name "Hedgehog". Length is not the test: a tweet qualifies the same as an essay. Does not apply to a…