self-use-luna-subagent SKILL.md skillA
self-use-luna-subagent from alice39s/agent-stash is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add alice39s/agent-stash/self-use-luna-subagent@git:20261025.742afa9Pins git:20261025.742afa9 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- alice39s/agent-stash
- Path
skills/self-use-luna-subagent/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261025.742afa9, committed Oct 25, 2026
- Size
- 6,010 bytes
- Repository stars
- 20
- License
- Apache-2.0
把任务委托给 GPT-5.6 Luna 子代理（gpt-5.6-luna，默认 high）时读本技能。单个子代理的上下文按 200k 规划；子代理不会压缩上下文，用到窗口上限就被终止，不留收尾消息，没写进文件的结果全部丢失。准备用 GPT-5.6 Luna 派发任务、估算一个子代理能做多少、写子代理提示词，或者它报告 ran out of room 时使用。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 用 GPT-5.6 Luna 当子代理
## 调用方式
`subagent({ provider: "aigw", model: "gpt-5.6-luna", reasoning_effort: "high", ... })`
`provider` 是 DeepSeek Harness（DSH）provider 配置里的名字，换了环境就改成自己配的那一项。派发之前用 `list_subagent_models` 确认 model id 和档位都还能用。
`reasoning_effort` 按任务规模在 `high`、`xhigh`、`max` 之间选，任务越大档位越高，拿不准时用 `high`。
## 上下文预算
单个子代理的总用量控制在 200k 以内，provider 配置里的 contextWindow 也建议设成 200000。
子代理不会自动压缩上下文。用量碰到 contextWindow 时，DSH 直接终止它，返回 `ran out of room`。这时没有收尾消息，还没写进文件的结论全部丢失。
派发任务之前先估算一遍：
| 内容 | 大致占用 |
| ----------------------------------------------------- | ---------- |
| 系统提示词、工具声明和任务提示词 | 15k 到 25k |
| 用 `web_fetch` 读一整页网页或文档 | 10k 到 40k |
| 一个源码文件，例如 raw.githubusercontent.com 上的文件 | 5k 到 20k |
| 一次没有截断的部署或构建输出 | 5k 到 15k |
| 一次 `docker ps`、`ss -ltnp` 这类列表 | 2k 到 5k |
扣掉固定开销和 5k 左右的余量，留给任务本身的大约是 170k。估出来比这个多，就先把任务分成更小的几份再派发。
## 一个子代理做多少事
一个子代理只交付一样东西，并且同时满足下面几条：
- 只有一个产出物：一个文件、一个脚本，或者一份调研报告。
- 最多读 5 个外部网页或 10 个源码文件。资料比这多的时候，主代理先把要点查好写进共享文件，再派发子代理。
- 最多对一个远端系统做写操作。
- 预计 35 次工具调用以内能做完。
拿不准时这样判断：一个没有其他背景、只读过这份提示词的人，能不能在一小时内做完。做不完就把任务再分小一些。
…Read the whole file at its exact version.
How to install
mdr add alice39s/agent-stash/self-use-luna-subagent@sha256:35b18bec7eea7088The line at the top of this page pins the label git:20261025.742afa9, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_up34n3kwloycgnik)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 25, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6010 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
alice39s/agent-stash · 20 stars · license Apache-2.0 · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_up34n3kwloycgnik GET https://markdownregistry.com/api/v1/resolve?ref=alice39s/agent-stash/self-use-luna-subagent GET https://markdownregistry.com/api/v1/blob/35b18bec7eea70886b8aeead9fcd920e330a0ca7095b5cd037e7e0f62d0ca108
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.