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/codelably/harmony-claude-code/oneskillnpx skills add codelably/harmony-claude-code --skill oneskillgit clone --depth 1 https://github.com/codelably/harmony-claude-codeWhat 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 | $0.00021 | $0.00788 |
| Opus 5 | $0.00010 | $0.00394 |
| Sonnet 5 | $0.00004 | $0.00158 |
| Haiku 4.5 | $0.00002 | $0.00079 |
Grade A, and why
oneskill 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 2d 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.
This is a copy
92% identical to oneskill — 28 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
OneSkill 元管理器 (Meta-Manager)
使用此技能来发现新功能、优化搜索查询，并使用 OpenSkills 简化技能设置。这为扩展环境功能提供了一种统一的方式。
何时使用
- 当用户要求的某些功能你目前不具备时。
- 当任务复杂、属于特定领域，或在尝试 2 次后仍被反复阻断时。
- 当可能存在更好的技能（Skill）时（例如：网页浏览、GitHub 集成、数据库管理、云基础设施）。
工作流 (Workflow)
- 搜索注册表：
- 运行：
npx oneskill search "<query>" [options] - 支持的选项：
--category、--limit、--offset、--sort。 - 示例：
npx oneskill search "browser" --sort starsnpx oneskill search "" --category database --limit 5
- 运行：
- 分析结果：
- 确定最佳匹配项，或优化查询并再次搜索。
- 与用户确认：
- 说明该技能的功能及其来源。
- 在获得明确批准后进行安装（使用 openskills）：
- 运行：
npx openskills install <slug-or-repo> - 示例：
npx openskills install anthropics/skills
- 运行：
- 处理特定环境的设置：
- Gemini CLI 用户：
openskills不会自动配置 Gemini。安装后你必须运行映射命令：npx oneskill map --target gemini（如果是全局安装，请添加--global）
- Gemini CLI 用户：
- 应用新技能以完成原始请求。
OpenSkills 基础
npx openskills install <source> [options]# 从 GitHub、本地路径或私有仓库安装npx openskills sync [-y] [-o <path>]# 更新 AGENTS.md (或自定义输出)npx openskills list# 显示已安装的技能npx openskills read <name># 加载技能（供智能体 (Agent) 使用）npx openskills update [name...]# 更新已安装的技能（默认：全部）npx openskills manage# 移除技能（交互式）npx openskills remove <name># 移除特定技能
示例：
npx openskills install anthropics/skillsnpx openskills sync
默认设置：安装在项目本地（./.claude/skills，或者带 --universal 参数安装在 ./.agent/skills）。使用 --global 安装在 ~/.claude/skills。
安全提示 (Safety Reminders)
- 未经用户明确确认，请勿安装。
- 除非用户同意覆盖现有目标，否则避免使用
--force-map。 - 使用 openskills 进行安装/更新；OneSkill 仅为 Gemini 提供搜索和映射。
- 对于 Gemini，请在安装后运行
npx oneskill map --target gemini。 - 默认安装/映射是项目本地的，与 openskills 相同；全局安装请使用
--global。 - 安装 OneSkill 本身时，建议使用
--global，以便在跨项目时可用。
What ships with it
28 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.
- .gitignore 1.3 KB
- .openskills.json 173 B
- LICENSE 9.9 KB
- package-lock.json 64 KB
- package.json 818 B
- README_CN.md 3.0 KB
- README.md 2.7 KB
- src/cli.ts 2.9 KB runs code
- src/commands/doctor.ts 632 B runs code
- src/commands/info.ts 380 B runs code
- src/commands/list.ts 486 B runs code
- src/commands/map.ts 666 B runs code
- src/commands/search.ts 823 B runs code
- src/commands/sync.ts 642 B runs code
- src/core/fs.ts 896 B runs code
- src/core/lock.ts 711 B runs code
- src/core/log.ts 426 B runs code
- src/core/manifest.ts 824 B runs code
- src/core/map.ts 1.6 KB runs code
- src/core/mapping.ts 2.7 KB runs code
- src/core/openskills.ts 1.3 KB runs code
- src/core/registry.ts 4.3 KB runs code
- src/core/root.ts 1.2 KB runs code
- src/core/types.ts 1.5 KB runs code
- src/core/versions.ts 879 B runs code
- src/utils/json.ts 113 B runs code
- tsconfig.json 279 B
- tsup.config.ts 183 B runs code
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.
- 2d ago First seen · 60 lines · 21 tokens per session scan A 940ec834bd51
oneskill is a skill published in the GitHub repository codelably/harmony-claude-code (42 stars, last pushed 6mo ago), licensed MIT. It adds 21 tokens to every session and 788 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to oneskill, differing in 28 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.