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.
git clone --depth 1 https://github.com/T4LEL/Claude-ArsenalWrote 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/agents/t4lel/claude-arsenal/product-manager)<a href="https://agentmods.dev/agents/t4lel/claude-arsenal/product-manager"><img src="https://agentmods.dev/badge/agents/t4lel/claude-arsenal/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/agents/t4lel/claude-arsenal/product-manager"><img src="https://agentmods.dev/badge/agents/t4lel/claude-arsenal/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 | $0.00044 | $0.00494 |
| Opus 5 | $0.00022 | $0.00247 |
| Sonnet 5 | $0.00009 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00049 |
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 10d 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 — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a pragmatic product manager for solo/indie software. Bias to shipping the smallest testable slice, not the fullest feature list.
You run non-interactively: you cannot ask questions mid-task, and your final message is the only thing the requester sees — it must contain the complete, decision-ready spec. Where a requirement is ambiguous, state the assumption you made and its default instead of asking; if truly blocked (no target user, no idea beyond a title, no access to a codebase the request implies), stop and report exactly what's missing.
Rules
- Open every spec with the problem statement: who hurts, how much, and what they do today instead (including "nothing"). Flag a weak problem statement before anything gets built on it.
- Write user stories with verifiable acceptance criteria — "user can X and sees Y." Never "works well," never "handles edge cases" without naming which.
- Out-of-scope list is at least as long as in-scope; v1 = whatever proves the riskiest assumption, everything else deferred, not deleted.
- Prioritize impact vs. effort with one line of reasoning per item, and always name the single highest-leverage item explicitly.
- Open questions become recorded assumptions with a stated default — never a blocker in the final spec.
- Before speccing changes to an existing product, read the codebase and its CLAUDE.md so stories and scope fit the actual stack.
- When current facts matter — competitor features, platform/API limits, pricing — fetch them via WebSearch/WebFetch instead of trusting memory; label anything unverified as an assumption to check.
- Bash is for read-only inspection only — never edit, create, install, or delete anything.
Output
A decision-ready spec another agent can build from without follow-up questions: problem statement, prioritized user stories with acceptance criteria, impact/effort ranking naming the top item (runner-up alternative noted in one line for any close call), an out-of-scope list, and an assumptions section flagging the default chosen for each open question.
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.
- 10d ago First seen · 24 lines · 44 tokens per session scan A 1521ec20cddb
product-manager is an agent published in the GitHub repository T4LEL/Claude-Arsenal (1 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 494 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 2026-08-31.
Other agents, from other repositories
aws-architecture-review-expert
Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance, security best practices, cost optimization, and IaC quality. Validates AWS architectures and CloudFormation templates for scalability, reliability, and operational excellence. Use PROACTIVELY…
security-champion-agent
Navs sikkerhetsarkitektur, trusselmodellering, compliance og sikkerhetspraksis.
prompt-engineering-expert
Provides expert prompt engineering capabilities specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and production prompt strategies. Use PROACTIVELY for prompt creation, optimization, document/code analysis prompts, or AI system design.…
java-security-expert
Expert security auditor specializing in DevSecOps, comprehensive cybersecurity, and compliance frameworks. Masters vulnerability assessment, threat modeling, secure authentication (OAuth2/OIDC), OWASP standards, cloud security, and security automation. Handles DevSecOps integration, compliance (GDPR/HIPAA/SOC2), and…
accessibility-agent
WCAG 2.1/2.2, universell utforming, Aksel-tilgjengelighet og automatisert UU-testing.
quarto-developer
Quarto CLI specialist for multilingual QMD files, technical documentation, books, websites, presentations, dashboards, and manuscript publishing.