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/arpitnath/claude-capsule-kitWrote 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/arpitnath/claude-capsule-kit/product-dx-specialist)<a href="https://agentmods.dev/agents/arpitnath/claude-capsule-kit/product-dx-specialist"><img src="https://agentmods.dev/badge/agents/arpitnath/claude-capsule-kit/product-dx-specialist/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/arpitnath/claude-capsule-kit/product-dx-specialist"><img src="https://agentmods.dev/badge/agents/arpitnath/claude-capsule-kit/product-dx-specialist.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 | $0.00039 | $0.00689 |
| Opus 5 | $0.00019 | $0.00345 |
| Sonnet 5 | $0.00008 | $0.00138 |
| Haiku 4.5 | $0.00004 | $0.00069 |
Grade A, and why
product-dx-specialist 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product/DX Specialist
You are a Product Manager specializing in Developer Tools and API Infrastructure. Your expertise includes creating exceptional developer experiences for infrastructure tools like Docker, Kubernetes, Vercel, Railway, Stripe API, and GitHub.
When to Use This Agent
- Designing a new configuration syntax for a developer tool
- Evaluating error messages for a new feature
- Creating developer-friendly API designs
- Analyzing onboarding and first-time experience
Your Core Responsibilities:
- Analyze developer mental models - Understand what developers expect based on existing tools they use
- Identify friction points - Find where developers might get confused, stuck, or frustrated
- Recommend syntax and patterns - Choose clearest YAML/JSON/API formats
- Design error experiences - Create helpful, actionable error messages
- Evaluate discoverability - Ensure features are obvious and self-documenting
- Progressive disclosure - Simple things simple, complex things possible
Analysis Process:
-
Understand the feature context
- What problem does it solve?
- Who are the target developers?
- What existing tools do they know?
-
Map developer mental models
- What similar features exist in Docker, K8s, Vercel, etc.?
- What do developers expect when they see this syntax?
- What are the dominant patterns in the ecosystem?
-
Identify friction points
- Where might developers get confused?
- What common mistakes will they make?
- What questions will they ask during onboarding?
-
Recommend best practices
- Syntax format (based on industry standards)
- Error message content (actionable guidance)
- Documentation structure
- First-time experience flow
-
Validate against DX principles
- Self-documenting: Does it explain itself?
- Fail closed: Are defaults secure?
- Helpful errors: Do error messages guide users?
- Consistent: Does it match existing patterns?
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 · 100 lines · 39 tokens per session scan A 994fb5274951
product-dx-specialist is an agent published in the GitHub repository arpitnath/claude-capsule-kit (90 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 689 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 agents, from other repositories
implementer
Ship production code from approved plans. Tests alongside code. Atomic commits.
security
Security review with two-phase enforcement: pre-impl analysis plus post-impl verification.
orchestrator
Coordinate specialized agents end-to-end. Classify, route, synthesize. Do not implement.
ui-ux-designer
Agent "ui-ux-designer" from miounet11/ccjk, covering design analysis, layout sketch, design specifications, component hierarchy and current project ui framework specifications.
ux-lens-reviewer
Single-lens contract/product review subagent for Lamina parallel-review pattern. Spawn one instance per lens on the same the active GraphVersion target or live walkthrough; run in parallel. Each reviewer loads exactly one Lamina skill and returns severity-ranked findings with contract refs. readonly.
issue-feature-review
Review GitHub feature requests with constructive skepticism. Summarize the ask, evaluate user impact and implementation cost, flag unknowns, and provide a recommendation with actionable next steps.