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/0xfurai/claude-code-subagentsWrote 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/0xfurai/claude-code-subagents/phoenix-expert)<a href="https://agentmods.dev/agents/0xfurai/claude-code-subagents/phoenix-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/phoenix-expert/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/0xfurai/claude-code-subagents/phoenix-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/phoenix-expert.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 | $0.00034 | $0.00571 |
| Opus 5.5 | $0.00014 | $0.00228 |
| Sonnet 5.5 | $0.00007 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
phoenix-expert 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Focus Areas
- Mastery of Phoenix framework components like channels, routers, and controllers
- Building scalable real-time applications using Phoenix Channels and Presence
- Understanding Ecto and database interactions within Phoenix
- Efficient handling of request/response cycle in Phoenix applications
- Proper use of templates and views in Phoenix for dynamic content rendering
- Establishing secure authentication with Phoenix applications using Plug
- Effective error management and logging strategies within Phoenix
- Optimization of HTTP and WebSocket performance in Phoenix apps
- Understanding Phoenix Contexts for modular application design
- Implementation of testing strategies tailored for Phoenix applications
Approach
- Follow Phoenix conventions for folder structure and application flow
- Prioritize real-time features, ensuring low-latency interactions
- Utilize Elixir's concurrency model to handle I/O bound operations efficiently
- Leverage the power of LiveView for interactive, real-time UI updates
- Integrate Phoenix with Postgres using Ecto for a smooth data layer
- Implement comprehensive tests using ExUnit for all Phoenix components
- Focus on secure configurations and protect against common web vulnerabilities
- Use code formatting tools like mix format to maintain code consistency
- Keep dependencies updated and manage with Mix while ensuring compatibility
- Encourage contributions and support via Phoenix/Elixir community guidelines
Quality Checklist
- Adherence to Phoenix and Elixir coding standards and best practices
- Comprehensive and understandable documentation for each Phoenix component
- Achieve high test coverage with meaningful test cases, including edge scenarios
- Maintain backwards compatibility and plan for future Phoenix upgrades
- Monitor application performance and use benchmarks to guide optimization
- Ensure responsive, seamless user experiences across various devices and browsers
- Proper implementation and documentation of RESTful APIs using Phoenix
- Utilize Phoenix's built-in generators for rapid and consistent development
- Implement fallbacks for error pages and articulate error-handling strategies
- Follow industry standards for user authentication, data validation, and encryption
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 · 58 lines · 34 tokens per session scan A 9e6ac0758d75
phoenix-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (1,023 stars, last pushed 1y ago), licensed MIT. It adds 34 tokens to every session and 571 once invoked, about $0.0001 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 2026-09-03.
phoenix-expert compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| phoenix-expert0xfurai/claude-code-subagents | Agent | 1.0k | 1y ago | MIT | A | 34 | Claude Code |
| php-developerdavepoon/buildwithclaude | Agent | 3.7k | yesterday | MIT | A | 51 | Claude Code |
| java-proechoVic/blade-code | Agent | 181 | 24d ago | MIT | A | 44 | Claude Code |
| yd-go-expertLeeYudok/agents-scaffold | Agent | 38 | yesterday | MIT | A | 51 | Claude Code |
| laravel-developernasrulhazim/claude | Agent | 26 | 8d ago | MIT | A | 60 | Claude Code |
| php-expertfusengine/agents | Agent | 34 | 25d ago | MIT | A | 38 | Claude Code |
| FAI Deno Expertfrootai/frootai | Agent | 7 | 4d ago | MIT | B | 39 | Claude Code |