github-outside-sandbox
Run Git and GitHub CLI commands on the host when sandboxing blocks Keychain auth, network access, or .git writes. Use for gh auth, repo/PR operations, index.lock, or permission errors; covers execution context only.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 4.3k
- Forks
- 626
01 前言 Front Matter
- name
- github-outside-sandbox
- description
- Run Git and GitHub CLI commands on the host when sandboxing blocks Keychain auth, network access, or .git writes. Use for gh auth, repo/PR operations, index.lock, or permission errors; covers execution context only.
02 资源文件 1
- 参考文档agents/openai.yaml282 B
03 SKILL.md 正文
GitHub Outside Sandbox
- Start normally. Escalate only the blocked command and only within the user's authorization.
- If sandboxed
gh auth statusfails, rerun it outside the sandbox before claiming authentication is broken. Never expose or copy tokens. - Run GitHub CLI network operations outside the sandbox when required:
gh repo ...,gh pr ..., and relatedghcommands. - Run Git writes outside the sandbox when
.gitis outside writable roots or errors mentionindex.lockorOperation not permitted:git add,git commit, andgit push. - Use the harness's official host-execution mechanism. In Codex, set
sandbox_permissions: "require_escalated", give a concretejustification, and use only a narrow safeprefix_rulewhen appropriate. - Never use shell wrappers, credential copying, or broad approval prefixes to bypass the sandbox.
- Verify from the host context with
git status -sb,git remote -v, and the relevantgh ... viewcommand. Ask the user to authenticate only if the host-context check also fails.
04 同仓库更多 Skills
varied-search
Research a topic across the web, GitHub, and X/Twitter with DeepAPI and produce a concise Markdown report. Use for varied-search or requests to compare web coverage, relevant repositories, and social discussion.
total-review
Run five independent max-effort reviews (Fable 5.1, Opus 5.5, GPT-6 Astra, GPT-6.1 Sol, Muse Wonder), merge their findings, and fix only what the user approves. Use for /total-review, or when the user or another agent asks for a total review.
stop-overthinking
Manually-invoked skill that stops overthinking and forces a short, practical decision. Use only when the user explicitly invokes stop-overthinking.
state
Manually-invoked skill that recaps what the current thread is doing and how far along it is. Use when the user says "state", "where are we", or "what % are we done".
setup-help
Guide setup one step at a time and show what remains. Use only when the user explicitly asks for it by name.
self-archive
Archive the current Cloudroom thread and release its runtime. Use only when the user explicitly asks to self-archive, archive yourself, or archive this thread.