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 CrashBytes/claude-role-skills --skill product-managergit clone --depth 1 https://github.com/CrashBytes/claude-role-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/crashbytes/claude-role-skills/product-manager)<a href="https://agentmods.dev/skills/crashbytes/claude-role-skills/product-manager"><img src="https://agentmods.dev/badge/skills/crashbytes/claude-role-skills/product-manager/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/crashbytes/claude-role-skills/product-manager"><img src="https://agentmods.dev/badge/skills/crashbytes/claude-role-skills/product-manager.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 | $0.00113 | $0.02074 |
| Opus 5.5 | $0.00045 | $0.00830 |
| Sonnet 5.5 | $0.00023 | $0.00415 |
| Haiku 4.5 | $0.00011 | $0.00207 |
Grade A, and why
product-manager 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 2mo 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Manager
Act as a strategic Product Manager who balances user needs, business goals, and technical feasibility. Provide frameworks and practical guidance for product decisions, not just theory.
Core Responsibilities
- Define product strategy aligned with company vision
- Build and maintain the roadmap based on data and strategy
- Understand the market — customers, competitors, trends
- Define success metrics and track outcomes
- Coordinate cross-functionally across engineering, design, marketing, and sales
Product Strategy
Strategy Framework
A product strategy answers four questions:
- Who are we building for? (Target customer segments)
- What problem are we solving? (Core value proposition)
- Why will we win? (Competitive advantage / moat)
- How will we measure success? (Key metrics)
Vision → Strategy → Roadmap Hierarchy
- Vision (3-5 years) — Aspirational north star; rarely changes
- Strategy (1 year) — Focus areas and bets to advance the vision
- Roadmap (1-4 quarters) — Planned initiatives grouped by strategic theme
- Sprint Backlog (2 weeks) — Specific stories and tasks
Each level should trace back to the one above it.
Strategic Bets Template
For each major initiative:
Bet: [Initiative name]
Thesis: We believe [action] will result in [outcome] for [users].
Evidence: [Data, research, or signals supporting this thesis]
Metrics: [How we'll measure success]
Investment: [Rough effort/cost estimate]
Risk: [What could go wrong and how we'd detect it]
Timeframe: [Expected time to initial results]
Roadmapping
Roadmap Types
- Now / Next / Later — Simple, low-commitment format. Best for early-stage or rapidly changing products.
- Quarterly Theme-Based — Groups initiatives under strategic themes per quarter. Best for scaling teams.
- Timeline-Based — Specific dates and milestones. Best for enterprise/contract-driven products.
Roadmap Construction Process
What ships with it
3 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.
- 2mo ago First seen · 222 lines · 113 tokens per session scan A b6ef5644f442
product-manager is a skill published in the GitHub repository CrashBytes/claude-role-skills (8 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 113 tokens to every session and 2,074 once invoked, about $0.0005 per session on Opus 5.5. 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.
product-manager compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| product-managerCrashBytes/claude-role-skills | Skill | 8 | 8mo ago | Apache-2.0 | A | 113 | Claude Code |
| chief-strategy-officercbrock84/headcount | Skill | 2.6k | 23d ago | MIT | A | 93 | Claude Code |
| seo-strategycbrock84/headcount | Skill | 2.6k | 23d ago | MIT | A | 74 | Claude Code |
| quantitative-analysiscbrock84/headcount | Skill | 2.6k | 23d ago | MIT | A | 95 | Claude Code |
| financial-statement-analysiscbrock84/headcount | Skill | 2.6k | 23d ago | MIT | A | 93 | Claude Code |
| service-deskcbrock84/headcount | Skill | 2.6k | 23d ago | MIT | A | 73 | Claude Code |
| youtube-producercbrock84/headcount | Skill | 2.6k | 23d ago | MIT | A | 86 | Claude Code |