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 skills add TestAny-io/testany-agent-skills --skill skill-managergit clone --depth 1 https://github.com/TestAny-io/testany-agent-skillsWrote 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.
[](https://agentmods.dev/skills/testany-io/testany-agent-skills/skill-manager)<a href="https://agentmods.dev/skills/testany-io/testany-agent-skills/skill-manager"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/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.
<a href="https://agentmods.dev/skills/testany-io/testany-agent-skills/skill-manager"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/skill-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00060 | $0.02841 |
| Opus 5.5 | $0.00024 | $0.01136 |
| Sonnet 5.5 | $0.00012 | $0.00568 |
| Haiku 4.5 | $0.00006 | $0.00284 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SkillDock
本 skill 随独立的 skilldock 插件分发，可在 Codex 或 Claude 中使用，仅打开本地技能管理应用。两边打开的是同一个本地实例和同一份数据。在支持原生入口的 Codex 版本中，可从 More / Explore 的 SkillDock 打开完整主页面并固定到侧栏；在 Claude 中把本地技能管理器打开在内置浏览器面板里。GUI 按钮直接调用本地服务，打开即加载本机技能库。用户只要求打开界面时，不替其安装、禁用或移除实际技能。
Codex 原生入口
仅 Codex 有此入口（Claude 不加载它）。插件随包提供本地 MCP 服务及完整 UI。新会话/重载后，在 More / Explore 选择 SkillDock；可用 Pin to sidebar 固定。第一次打开会自动准备后台，后续复用已核实的实例。全局页面沿用已保存的项目，首次无选择时用用户主目录，用户可从项目选择器切换。后台中断时界面会重连，不自动重放写操作。原型 SkillDock Preview 是不同测试插件，正式入口需单独固定；不自动卸载用户的 Preview。
分发和生命周期说明见 原生应用接入。
启动与打开
从本次实际加载的 SKILL.md 所在目录定位 scripts/launch.sh，不要假定仓库 checkout 或插件缓存路径。启动器按固定顺序查找本机 Node.js 22.12+（Codex 工作区、已下载的专用版本、Homebrew、nvm/fnm/Volta/asdf/mise/nodenv、PATH），保存所选路径供两侧入口与后台任务复用，失效时重新查找；找不到时弹出安装引导（打开下载页或安装后“重新检测”），不再自动下载。
/bin/sh "/实际安装位置/skill-manager/scripts/launch.sh" start --project "/用户项目的绝对路径"
启动前确定用户项目目录，并用 --project 显式传入；不要先切换到下载目录或安装目录再把它作为用户项目。未指定时依次使用 SKILLDOCK_PROJECT_DIR、界面保存的项目、调用工作目录。界面“切换项目”可保存新的扫描选择。可用 SKILLDOCK_STATE_DIR 指定独立应用数据目录、PORT 指定端口；默认数据位于 ~/.local/share/skilldock，默认端口 4771。启动器把源文件复制到应用数据目录，按 lockfile 安装依赖并构建（输出写入数据目录的 build.log），不向安装的插件缓存写入运行数据。首次启动需要 npm registry 可达，后续复用相同构建。
Codex CLI 逐个验证 PATH、桌面应用内置 CLI 与 Codex 管理的副本；损坏的旧 wrapper 会被跳过。Claude 命令行依次取显式指定、用户手动指定的保存值、从 Claude 打开时会话提供的路径、Claude 桌面应用自带的最高版本、此前自动选中的保存值、PATH 与用户目录下的安装，选中后保存并在使用前核验版本，因此会跟上 Claude 的升级。指定 SKILLDOCK_CODEX_BIN 或 SKILLDOCK_CLAUDE_BIN 时必须是有效的绝对路径。SkillDock 的服务与它调用的命令行只继承白名单内的环境变量，不带入宿主会话变量。CLI 诊断也包含在 doctor 中，实际来源说明见 应用安装说明。
运行环境发现失败时先执行 launch.sh doctor（只读，不写任何文件）。宿主若提供 load_workspace_dependencies，可读取其返回的真实 Node 路径，以 SKILLDOCK_NODE_BIN 指定；自定义 Codex 应用位置使用 SKILLDOCK_CODEX_APP_DIR。无人值守或没有图形界面的环境可设 SKILLDOCK_NO_DIALOG=1 关闭安装引导对话框。不要修改 Codex 的签名或用户 shell 配置来绕过加载限制。诊断及兼容边界见 运行环境接入。
核对启动前后打印的请求目录和最终扫描目录、目录来源、Codex CLI 绝对路径，以及本机有 Claude 时所选的 Claude 命令行。真实路径与请求路径不同会有符号链接说明；若最终目录不符合用户意图，修正 --project 后重新打开，不把 HTTP 200 当作扫描目录正确的证据。
What ships with it
60 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.
- assets/app/.gitignore 89 B
- assets/app/index.html 637 B
- assets/app/package-lock.json 99 KB
- assets/app/package.json 1.2 KB
- assets/app/playwright.config.ts 1.1 KB runs code
- assets/app/prototype/_delivery-summary.md 14 KB
- assets/app/prototype/_prototype-manifest.md 9.6 KB
- assets/app/prototype/_repo-survey.md 5.4 KB
- assets/app/prototype/.gitignore 53 B
- assets/app/prototype/components.tsx 5.0 KB
- assets/app/prototype/index.html 513 B
- assets/app/prototype/main.tsx 397 B
- assets/app/prototype/mock/data.ts 13 KB runs code
- assets/app/prototype/prototype.css 56 KB
- assets/app/prototype/Prototype.tsx 40 KB
- assets/app/prototype/README.md 3.3 KB
- assets/app/prototype/tsconfig.json 127 B
- assets/app/prototype/vite.config.ts 779 B runs code
- assets/app/prototype/Workspaces.tsx 25 KB
- assets/app/README.md 40 KB
- assets/app/scripts/brand-assets.mjs 1.5 KB runs code
- assets/app/scripts/native-bundle.mjs 3.4 KB runs code
- assets/app/scripts/node-candidates.mjs 1.5 KB runs code
- assets/app/scripts/source-bundle.mjs 11 KB runs code
- assets/app/server/agents.mjs 8.3 KB runs code
- assets/app/server/app-directory.mjs 9.2 KB runs code
- assets/app/server/background-entry.mjs 2.6 KB runs code
- assets/app/server/background-registration.mjs 4.1 KB runs code
- assets/app/server/background-worker.mjs 13 KB runs code
- assets/app/server/background.mjs 9.6 KB runs code
- assets/app/server/cache-paths.mjs 723 B runs code
- assets/app/server/claude-actions.mjs 28 KB runs code
- assets/app/server/claude-catalog.mjs 34 KB runs code
- assets/app/server/claude-cli.mjs 6.7 KB runs code
- assets/app/server/claude-plugin-updates.mjs 19 KB runs code
- assets/app/server/claude-root.mjs 3.6 KB runs code
- assets/app/server/claude-settings.mjs 5.4 KB runs code
- assets/app/server/claude-updates.mjs 5.8 KB runs code
- assets/app/server/claude-writer.mjs 5.5 KB runs code
- assets/app/server/cli.mjs 27 KB runs code
- assets/app/server/codex-runtime.mjs 2.9 KB runs code
- assets/app/server/config.mjs 7.2 KB runs code
- assets/app/server/direct-plugins.mjs 9.0 KB runs code
- assets/app/server/directory-icons.mjs 2.5 KB runs code
- assets/app/server/errors.mjs 743 B runs code
- assets/app/server/files.mjs 9.4 KB runs code
- assets/app/server/fixtures.mjs 5.7 KB runs code
- assets/app/server/gate-cli.mjs 7.3 KB runs code
- assets/app/server/generation.mjs 1.6 KB runs code
- assets/app/server/git-access.mjs 2.0 KB runs code
- assets/app/server/git-source.mjs 2.7 KB runs code
- assets/app/server/index.mjs 12 KB runs code
- assets/app/server/installation.mjs 2.7 KB runs code
- assets/app/server/installs.mjs 12 KB runs code
- assets/app/server/launch-plan.mjs 19 KB runs code
- assets/app/server/launcher-record.mjs 6.6 KB runs code
- assets/app/server/local-settings.mjs 3.1 KB runs code
- assets/app/server/migration.mjs 8.2 KB runs code
- assets/app/server/move.mjs 3.7 KB runs code
- assets/app/server/multi-agent.mjs 3.9 KB 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 Changed 502d6fc8c37f
- 3d ago Changed · +7 lines · +5 tokens per session a10e777a506d
- 7d ago Changed · +2 lines 6c8acec6b415
- 17d ago Changed · +6 lines bd431fc53811
- 23d ago Changed · +2 lines acf6b8b86c3c
- 1mo ago Changed · +10 lines e6c7ed6962b6
- 1mo ago First seen · 49 lines · 55 tokens per session scan A b5c4ae16bf76
skill-manager is a skill published in the GitHub repository TestAny-io/testany-agent-skills (82 stars, last pushed 3d ago), licensed MIT. It adds 60 tokens to every session and 2,841 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-15.
Other skills, from other repositories
web-test
A browser-automation tool for testing the 1C:Enterprise web client. It uses Playwright to navigate sections, fill forms, read tables and reports, and perform user actions in a browser.
form-edit
A tool for modifying an existing managed form in 1C by adding screen elements, fields, commands, and event handlers. Event handlers are code routines that run when something happens, such as a field changing.
cfe-patch-method
A generator for method interceptors in 1C extensions, which let an extension add code before or after an existing method or replace its body. It reads the original method and creates or updates the required BSL source file.
db-list
A command for listing and managing the 1C databases registered in a project's .v8-project.json file.
form-patterns
A reference guide for arranging managed forms in the 1C platform. It describes common layouts, naming conventions, events, properties, and advanced patterns for different form types.
mxl-compile
A generator for 1C MXL spreadsheet-document layouts from a compact JSON description. MXL is the 1C format used for tabular documents such as printable forms.