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/alice-space/alice/githubnpx skills add Alice-space/alice --skill githubgit clone --depth 1 https://github.com/Alice-space/aliceWhat 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 | $0.00090 | $0.00776 |
| Opus 5 | $0.00045 | $0.00388 |
| Sonnet 5 | $0.00018 | $0.00155 |
| Haiku 4.5 | $0.00009 | $0.00078 |
Grade A, and why
github 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
GitHub
优先使用 scripts/github.sh，并依赖当前机器上已经登录的 gh。这个 skill 主要为 Alice 当前的发布链路设计，但也能复用于同样遵循 dev -> main、merge commit、merge 后自动发 release 的仓库。
Quick Start
- 创建新的发行版：
scripts/github.sh create-release --repo-dir /path/to/repo - 更新 Alice 运行时到最新稳定版：
scripts/github.sh update-self --repo-dir /path/to/alice - 更新 Alice 运行时到指定版本：
scripts/github.sh update-self --repo-dir /path/to/alice --version vX.Y.Z
Workflow
- 先确认目标仓库的工作树干净，避免把未提交或无关改动推进 release。
- 对 Alice 仓库，默认发布路径固定为
dev -> main，合并方式固定为merge。 create-release会自动执行这些步骤：- 校验 Git 仓库、当前分支和工作树状态
- 推送
dev - 创建或复用
dev -> main的 open PR - 轮询 PR 状态，直到可以用 merge commit 合并
- 等待与 merge commit 对应的正式 GitHub Release 出现
update-self通过npm install -g @alice_space/alice@latest更新 Alice，然后重启 systemd 服务。
Guardrails
- 只有在仓库确实采用
dev -> main自动发布流程时才使用默认参数；Alice 仓库的固定规则见references/alice-release-flow.md。 create-release依赖gh auth status通过；脚本只通过gh使用当前机器上的 GitHub 登录态，不自己读取、拼接或打印 token。- 如果当前仓库存在未提交改动，先停下来，确认这些改动是否应该进入这次 release。
- 如果 PR 长时间停留在
blocked、behind或dirty，不要强行改写分支；先检查分支保护、必需检查项或冲突原因。
Alice Repo Notes
- 读
references/alice-release-flow.md获取 Alice 仓库的分支与发布约束。 update-self默认更新 stable release；只有用户明确要求时才加--channel dev。- 发布完成后，在回复里给出 PR 编号、merge commit SHA、release tag 和 release URL。
Response Pattern
- 明确说明执行的是
create-release还是update-self。 - 对 release 流程，回复里带上：
- 仓库名
- PR 编号
- merge commit SHA
- release tag 和 URL
- 对自更新，回复里带上：
- 使用的仓库
- channel / version
ALICE_HOME或显式--home
- 如果因为
gh未登录、分支状态异常或仓库不匹配而未执行，明确说明阻塞点和下一步。
What ships with it
3 files 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 · 57 lines · 90 tokens per session scan A 64831fd16c4c
github is a skill published in the GitHub repository Alice-space/alice (5 stars, last pushed 26d ago), licensed MIT. It adds 90 tokens to every session and 776 once invoked, about $0.0005 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
antfu
Anthony Fu's opinionated tooling and conventions for JavaScript/TypeScript projects. Use when setting up new projects, configuring ESLint/Prettier alternatives, monorepos, library publishing, or when the user mentions Anthony Fu's preferences.
conventional-commits
Conventional Commits specification for consistent, machine-readable git commit messages. Use when crafting commit messages, enforcing commitlint rules, or generating changelogs/releases.
chatbot-mvp-distillation
Distill the chatgpt-vue3-light-mvp project into reusable architecture for building similar ChatGPT-style web products in other repositories. Use when designing or implementing streaming chatbot UIs, SSE/fetch response pipelines, model adapter contracts, typewriter rendering, Markdown/code/KaTeX/Mermaid rendering…
chatbot-mvp-distillation-zh
将 chatgpt-vue3-light-mvp 项目蒸馏为可迁移到其他项目的中文架构指南。适用于设计或实现类似 ChatGPT 的 Web 对话产品，包括 SSE/fetch 流式响应、模型适配器契约、打字机渲染、Markdown/代码/KaTeX/Mermaid 渲染、推理过程展示，以及从本 Vue 3 MVP 迁移到其他项目的方案规划。.
ui-aesthetics
Raise frontend visual judgment for web interfaces with a bias toward refined product-grade composition, precise component craftsmanship, disciplined interaction states, controlled motion, and coherent depth systems. Use when generating, reviewing, or refactoring web UI that feels generic, cluttered, flat, over-styled…
deepseek-harness
Use this skill whenever the user wants to call DeepSeek V4-Pro / V4-Flash (or its legacy aliases deepseek-chat / deepseek-reasoner), or you see code that imports from openai import OpenAI with baseurl="https://api.deepseek.com". This skill teaches you the 10 protocol contract rules required to avoid the 16 documented…