baku-skill-manager

baku-skill-manager is a skill for Codex from Basic-XYZ/baku-skills. It costs 85 tokens per session (1,097 once invoked), scanned A, original, MIT.

A manager for installing, updating, linking, merging, and removing shared coding-agent skills across Codex and Claude Code.

In plain words
What is it for?
Use it to check skill status, adopt installed skills, update them, resolve merge conflicts, create links for supported agents, or sync usage records.
Why use it?
It keeps one canonical skill copy, preserves local changes during updates, and requires conflicts or destructive actions to be handled explicitly.

Skill for Codex

Written for Codex: reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

Good fit Use it to check skill status, adopt installed skills, update them, resolve merge conflicts, create links for supported agents, or sync usage records.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/basic-xyz/baku-skills/baku-skill-manager
Install

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.

Any agent
npx skills add Basic-XYZ/baku-skills --skill baku-skill-manager
Clone the repo
git clone --depth 1 https://github.com/Basic-XYZ/baku-skills

Made for: Codex.

Wrote 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.

agentmods badge for baku-skill-manager

README.md
[![agentmods](https://agentmods.dev/badge/skills/basic-xyz/baku-skills/baku-skill-manager/github.svg)](https://agentmods.dev/skills/basic-xyz/baku-skills/baku-skill-manager)
Your own site
<a href="https://agentmods.dev/skills/basic-xyz/baku-skills/baku-skill-manager"><img src="https://agentmods.dev/badge/skills/basic-xyz/baku-skills/baku-skill-manager/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.

agentmods 80×15 button for baku-skill-manager

Your own site · 80×15
<a href="https://agentmods.dev/skills/basic-xyz/baku-skills/baku-skill-manager"><img src="https://agentmods.dev/badge/skills/basic-xyz/baku-skills/baku-skill-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,097 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00085 $0.01097
Opus 5 $0.00043 $0.00549
Sonnet 5 $0.00017 $0.00219
Haiku 4.5 $0.00009 $0.00110

Measured 12d ago against content hash 8a82c6ea32c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

baku-skill-manager 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.

baku-skill-manager/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Baku Skill Manager

这个 skill 是自然语言入口,实际文件管理必须交给仓库里的 skills CLI;不要在对话里手工复制、覆盖或删除 Skill 目录。

全局目录合同

  • 真实 Skill 文件只放在 ~/.agents/skills/<name>
  • Codex 使用 ~/.codex/skills/<name> 软链接。
  • Claude Code 使用 ~/.claude/skills/<name> 软链接。
  • manager 状态放在 ~/.agents/.manager/
  • 不扫描、不管理项目目录里的 Skill。
  • 全局扫描会排除 .DS_Store.agents.claude.packages.playwright.system,这些目录不会被当作 Skill 认领。

调用规则

先执行只读命令确认当前状态:

skills status <name>
skills check <name>

官方 npx skills add 安装后,使用 adopt 认领,而不是再次复制一份:

skills adopt --skill <name>
skills adopt --skill <name> --source <owner/repo>
# 多个现有目录内容不同时显式选择 canonical 来源
skills adopt --skill <name> --prefer codex --yes

如果没有来源,只能登记为 local-only,不要猜来源;只有提供准确来源后才允许更新。

更新规则

更新前先展示上游 commit、本地改动和差异。更新命令会在本机记录 local commit,并以“上次安装基线 + 本地改动 + 上游新 commit”做三方合并:

skills diff <name>
skills update <name>
skills resolve <session-id> --ours
skills resolve <session-id> --theirs

无冲突部分自动合并;冲突必须保留 pending session,不能静默覆盖。批量更新必须显式使用 skills update --all

启动本地管理页面,并同步 Codex 使用事件:

skills serve
skills usage sync

页面默认启动在 127.0.0.1:43127(可用 skills serve --port <port> 覆盖),按 Codex 本地会话中的累计使用次数降序展示 Skill,并按分组内最近 60 天使用次数降序排列分组;来源明确时展示 GitHub 地址,无法确认时标记为 local。页面支持按分组、名称和 local/remote 来源筛选,可修改分组名称、展开/收起分组、批量同步已绑定云端 Skill,以及通过 skills.sh 为本地 Skill 初始化云端来源。更新、批量操作和移除各弹出一次确认,并沿用 CLI 的三方合并、冲突 session 和本地备份规则。

“同步 Codex 技能使用记录”会扫描本地 Codex 会话并导入结构化使用事件;“同步云端 Skill”只处理已经登记 GitHub 来源的 Skill,行为等同于逐个点击“更新”;“初始化云端 Skill”只处理没有来源的 Skill,会搜索 skills.sh,并在仓库实际包含同名 Skill 后才绑定来源,不会覆盖本地文件。三个操作都会立即返回并在服务端后台执行,页面刷新不会中断,可通过任务状态恢复进度。

skills usage sync 只读扫描 ~/.codex/sessions~/.codex/archived_sessions,导入 Codex 会话里结构化的 <skill> 触发事件到 ~/.agents/.manager/usage.jsonl。同步按事件指纹幂等,不会重复计数。历史 Manager 手动事件仍保留在日志中,但不再计入页面统计。

Codex 个人资料页里的“最常用的插件”是账户级分析口径,数字可能高于本地会话中可解析的结构化事件;manager 不会把它们混用,也不会用文件访问时间猜测 Skill 是否被调用。

链接和卸载

skills link <name> --agent claude
skills unlink <name> --agent claude
skills remove <name>

Read the full file on GitHub · 78 lines

Changes

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.

  1. 12d ago First seen · 78 lines · 85 tokens per session scan A 8a82c6ea32c9

Subscribe to this mod's changes

baku-skill-manager is a skill published in the GitHub repository Basic-XYZ/baku-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 1,097 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

skills-manager-cli

Drive the Skills Manager CLI (skm) to initialize the hub, adopt unmanaged skills, list/enable/disable skills per AI tool, and doctor/fix symlink sync. Use whenever the user or an agent needs to manage skills from a terminal, SSH session, CI job, or headless machine; when a skill is missing in Claude Code, Codex…

jiweiyeah/Skills-Manager · 151 tokens

ppt-design-skill

Design, generate, review, and revise editable PowerPoint presentations through a rigorous brief-to-PNG workflow using the public pptx-designer Python library.

sunchaokun/PPT-Design-Skill · 35 tokens

cesiumjs-camera

CesiumJS camera control - Camera, flyTo, lookAt, setView, ScreenSpaceCameraController, CameraEventAggregator, flight animation. Use when positioning the camera, creating flyTo animations, constraining user navigation, tracking entities, or converting between screen and world coordinates.

CesiumGS/cesiumjs-skills · 61 tokens

cesiumjs-custom-shader

CustomShader authoring — vertexShaderText and fragmentShaderText against VertexInput, FragmentInput, FeatureIds, Metadata, czmmodelMaterial. Use when reading EXTmeshfeatures or EXTstructuralmetadata property textures/tables, vertex displacement, or shading VoxelPrimitive.

CesiumGS/cesiumjs-skills · 61 tokens

cesiumjs-primitives

CesiumJS primitives and geometry - Primitive, GeometryInstance, Appearance, BufferPrimitive collections, GeoJsonPrimitive, Billboard/Label/PointPrimitive collections, built-in geometry shapes, ground primitives, classification. Use when rendering performance-critical static or vector geometry, loading GeoJSON without…

CesiumGS/cesiumjs-skills · 76 tokens

cesiumjs-time-properties

CesiumJS time, properties, and animation - Clock, JulianDate, TimeInterval, Property, SampledProperty, CallbackProperty, PathMode, interval and sampled path materials, interpolation, splines, CZML temporal data. Use when making entity attributes or path materials time-dynamic, configuring the simulation clock…

CesiumGS/cesiumjs-skills · 84 tokens