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 agentmods add skills/proxyfan/proxyfan/code-healthnpx skills add Proxyfan/Proxyfan --skill code-healthgit clone --depth 1 https://github.com/Proxyfan/ProxyfanWhat 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 | $0.00036 | $0.00282 |
| Opus 5 | $0.00018 | $0.00141 |
| Sonnet 5 | $0.00007 | $0.00056 |
| Haiku 4.5 | $0.00004 | $0.00028 |
Grade A, and why
code-health 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 yesterday.
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.
What it actually says
You are the code-health specialist for Proxyfan. You evaluate the
small-scale shape of code: how a single file reads, whether names express
intent, whether a method has grown too long, whether a parameter list should
be a record. Your boundary with other specialists is strict — cross-file
structural duplication belongs to code-duplication, layer violations belong
to architect, and business semantics belong to domain-driven-design.
Workflow
Walk RULES.md (sibling) for each candidate finding. The rule list maps
each item to its enforcing analyzer ID (or to a Proxyfan convention).
Output
SEVERITY: [High | Medium | Low]
LOCATION: <file path>:<line range or class/method>
CATEGORY: Naming | Complexity | Duplication | Dead code | Abstraction | Parameters | Style | Out/Ref | Consistency
ISSUE: <concise description>
SUGGESTED FIX: <concrete recommendation>
Skip pure whitespace findings — .tools/Invoke-Cleanup.ps1 handles those on
demand. Order by severity. Summary count per severity at the end.
What ships with it
1 file 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.
- yesterday First seen · 30 lines · 36 tokens per session scan A 8a6411967778
code-health is a skill published in the GitHub repository Proxyfan/Proxyfan (2 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 282 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 skills, from other repositories
github-actions-pat
用 Personal Access Token 通过 GitHub REST API 分析 Actions CI 的失败 run/job/step、拉取日志、轮询运行状态、做 PR code review，并驱动 fix → push → watch → iterate 的闭环。Token 只从 GITHUBTOKEN 环境变量读取，不落盘、不回显。适合在 bifrost remote / CI 调度器 / 无头环境里跑。仓库锁定在 AGENTS.md 或调用处通过 GHREPO 显式指定。.
codex-task-inspector
Inspect Codex async task progress from the correct data directory. Use when the user asks to check Codex status, inspect async task progress, summarize task state, or determine whether local Codex workers are still running. Always detect the active Codex data dir first: prefer CODEXHOME when set, otherwise fall back…
juejin-publish
Publish Markdown articles and Bifrost capability series to Juejin, or verify with Microsoft Edge that a published Juejin page's title and body match the local Markdown. Use when the user asks to create, save, publish, or验收 a 掘金/Juejin article, automate future Bifrost article releases, reuse authentication from Bifrost…
zhihu-publish
Publish Markdown articles to Zhihu Columns through authentication context recovered locally from Bifrost traffic and a built-in publish payload schema, save drafts, prevent duplicate posts, and verify the live title/body without browser automation. Use when the user asks to create, preview, save, publish, repost, or验收…
e2e-verify
面向 Bifrost 管理端的端到端 UI 与 API 验证工具。 适用于浏览器测试、场景回归、管理端接口验证与页面快照排查。 Use when: 端到端验证、功能验证、E2E 测试、UI 测试、浏览器测试、API 测试、接口验证.
site-cookie-login
Open a target website, wait for user login, verify login with required cookies plus an HTTP probe, and save cookies into .env for later automation. Use this when a site needs controlled browser login, cookie persistence, and automatic login-state checks.