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 zeoloverbaby-bit/codex-quota-saver --skill luna-routinggit clone --depth 1 https://github.com/zeoloverbaby-bit/codex-quota-saverWrote 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/zeoloverbaby-bit/codex-quota-saver/luna-routing)<a href="https://agentmods.dev/skills/zeoloverbaby-bit/codex-quota-saver/luna-routing"><img src="https://agentmods.dev/badge/skills/zeoloverbaby-bit/codex-quota-saver/luna-routing/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/zeoloverbaby-bit/codex-quota-saver/luna-routing"><img src="https://agentmods.dev/badge/skills/zeoloverbaby-bit/codex-quota-saver/luna-routing.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 | $0.00050 | $0.00562 |
| Opus 5 | $0.00025 | $0.00281 |
| Sonnet 5 | $0.00010 | $0.00112 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
luna-routing 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 12d 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.
What it actually says
Luna 路由决策（本项目专用）
决策树
- 默认路径：主线程直接做。需求清晰、或委派开销 > 工作本身时，一律不 spawn。
- 重执行判定（全部满足才 spawn
luna_worker）：- ≥2 个真正独立、文件互斥、可单独验证的工作包；或单包大至需要保护主上下文
- 每包范围与验收标准明确
- 可写文件零重叠，每个文件只有一个 owner
- 主线程负责集成与验收
- 疑难决策（架构、安全、数据完整性、破坏性迁移、跨系统接口、两次基于证据的尝试失败）→ STOP 报告用户，等
.codex/next-step.md回流（网页 GPT 决策）。不在 Codex 内 spawn Sol 子代理。 - 禁止 spawn 的场景：单文件小改、查询/只读分析、Evidence 报告、文档更新、轻量修复。
执行包模板（派发给 worker 时）
目标：
可写范围（精确文件列表）：
不可触碰：
验收标准：
验证命令：
主线程模型切换（由用户手动控制）
- 默认 Luna：commit、merge、批量执行等常规/机械任务
- 高难度任务（架构、疑难 bug、复杂重构）：用户手动切 Sol（medium 档），完成后切回
- 本技能不改变模型选择；但若主线程为 Sol，路由判定更保守（spawn 门槛更高）
验证门槛
- 每个 worker 返回后核对：实际改动文件 ⊆ 授权范围；跑验收标准
- 集成由主线程完成，worker 不宣称最终验收
- 模型使用诚实条款：只有 agent 活动或工具结果明确标识
gpt-5.6-luna才可声称用了 Luna；首次 spawn 后核对 rollout 的实际模型（issue #32587：子代理可能静默继承父模型，如发生即报告用户）
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.
- 12d ago First seen · 40 lines · 50 tokens per session scan A c3b75f798a93
luna-routing is a skill published in the GitHub repository zeoloverbaby-bit/codex-quota-saver (5 stars, last pushed 18d ago), licensed MIT. It adds 50 tokens to every session and 562 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…