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 wecode-ai/Wegent --skill develop-wework-plugingit clone --depth 1 https://github.com/wecode-ai/WegentWrote 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/wecode-ai/wegent/develop-wework-plugin)<a href="https://agentmods.dev/skills/wecode-ai/wegent/develop-wework-plugin"><img src="https://agentmods.dev/badge/skills/wecode-ai/wegent/develop-wework-plugin/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/wecode-ai/wegent/develop-wework-plugin"><img src="https://agentmods.dev/badge/skills/wecode-ai/wegent/develop-wework-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00064 | $0.03112 |
| Opus 5.5 | $0.00026 | $0.01245 |
| Sonnet 5.5 | $0.00013 | $0.00622 |
| Haiku 4.5 | $0.00006 | $0.00311 |
Grade A, and why
develop-wework-plugin 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 1mo 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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Develop a Wework plugin
Treat the Wework package as the outer delivery unit. It may declare a nested
Codex plugin through wework.codexPlugin; the Codex plugin must never own or
gate the Wework plugin.
Use the bundled development kit
This Skill includes the complete public Wework extension catalog, one exhaustive smoke-test plugin, three focused API references, and three product-oriented showcase plugins:
- Read references/extension-points.md before choosing a UI surface. It documents descriptor fields, component props, and the browser-module boundary.
- Inspect assets/ui-extension-demo before writing a low-level UI contribution.
- Inspect assets/reference-plugins for runnable,
independently installable examples of Composer augmentation, persistent
workflow UI, website navigation, and typed desktop-host integration. For a
left-navigation button that opens a website in the Wework built-in browser,
start from
sidebar-browser-panel-demo. Copy only the closest example into the user's writable project, then delete every contribution the plugin does not need. - Start with assets/showcase-plugins when the user wants a product-quality example. Workspace Copilot, Test Explorer, and Dev Environments represent popular AI-assistant, testing, and development-environment categories with deliberately different interaction models.
- Never edit files inside an installed plugin cache. Resolve these resources relative to this Skill, and copy examples to the active project first.
The catalog covers all public host slots:
- Navigation and apps:
wework.action,wework.app,wework.route,wework.sidebar.navigation,wework.settings.page, andwework.settings.section. - Project and workspace:
wework.plugins.action,wework.project.create.section,wework.project.work.section,wework.workspace.menu.section,wework.workspace.tab,wework.workspace.sidebar.tab,wework.workspace.toolbar.action,wework.workspace.bottom-panel.tab, andwework.runtime-profile.workspace-policy. - Composer:
wework.composer.action. - Home and context:
wework.home,wework.task.status,wework.conversation.summary, andwework.board.card.status. - Shell:
wework.shell.before,wework.shell.after, andwework.shell.overlay.
What ships with it
47 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/reference-plugins/endpoint-watch-demo/client.js 19 KB runs code
- assets/reference-plugins/endpoint-watch-demo/cordis.patch.yml 86 B
- assets/reference-plugins/endpoint-watch-demo/index.js 69 B runs code
- assets/reference-plugins/endpoint-watch-demo/package.json 786 B
- assets/reference-plugins/endpoint-watch-demo/README.md 557 B
- assets/reference-plugins/focus-board-demo/client.js 15 KB runs code
- assets/reference-plugins/focus-board-demo/cordis.patch.yml 80 B
- assets/reference-plugins/focus-board-demo/index.js 66 B runs code
- assets/reference-plugins/focus-board-demo/package.json 780 B
- assets/reference-plugins/focus-board-demo/README.md 409 B
- assets/reference-plugins/prompt-library-demo/client.js 12 KB runs code
- assets/reference-plugins/prompt-library-demo/cordis.patch.yml 86 B
- assets/reference-plugins/prompt-library-demo/index.js 69 B runs code
- assets/reference-plugins/prompt-library-demo/package.json 793 B
- assets/reference-plugins/prompt-library-demo/README.md 464 B
- assets/reference-plugins/README.md 702 B
- assets/reference-plugins/reference-plugins.test.mjs 8.0 KB runs code
- assets/reference-plugins/sidebar-browser-panel-demo/client.js 1.3 KB runs code
- assets/reference-plugins/sidebar-browser-panel-demo/cordis.patch.yml 100 B
- assets/reference-plugins/sidebar-browser-panel-demo/index.js 76 B runs code
- assets/reference-plugins/sidebar-browser-panel-demo/package.json 807 B
- assets/reference-plugins/sidebar-browser-panel-demo/README.md 867 B
- assets/showcase-plugins/quality-guardian-demo/client.js 9.7 KB runs code
- assets/showcase-plugins/quality-guardian-demo/cordis.patch.yml 128 B
- assets/showcase-plugins/quality-guardian-demo/index.js 6.2 KB runs code
- assets/showcase-plugins/quality-guardian-demo/package.json 799 B
- assets/showcase-plugins/quality-guardian-demo/README.md 555 B
- assets/showcase-plugins/README.md 916 B
- assets/showcase-plugins/runtime-doctor-demo/client.js 13 KB runs code
- assets/showcase-plugins/runtime-doctor-demo/cordis.patch.yml 134 B
- assets/showcase-plugins/runtime-doctor-demo/index.js 4.4 KB runs code
- assets/showcase-plugins/runtime-doctor-demo/package.json 811 B
- assets/showcase-plugins/runtime-doctor-demo/README.md 710 B
- assets/showcase-plugins/showcase-plugins.test.mjs 8.7 KB runs code
- assets/showcase-plugins/workspace-copilot-demo/client.js 12 KB runs code
- assets/showcase-plugins/workspace-copilot-demo/cordis.patch.yml 136 B
- assets/showcase-plugins/workspace-copilot-demo/index.js 4.4 KB runs code
- assets/showcase-plugins/workspace-copilot-demo/package.json 798 B
- assets/showcase-plugins/workspace-copilot-demo/README.md 672 B
- assets/ui-extension-demo/client.js 16 KB runs code
- assets/ui-extension-demo/client.test.mjs 8.0 KB runs code
- assets/ui-extension-demo/cordis.patch.yml 90 B
- assets/ui-extension-demo/index.js 71 B runs code
- assets/ui-extension-demo/package.json 844 B
- assets/ui-extension-demo/README.en.md 1.7 KB
- assets/ui-extension-demo/README.md 1.6 KB
- references/extension-points.md 22 KB
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.
- 1mo ago Changed a2d299686db5
- 1mo ago Changed · +2 lines c0f6a62dc86f
- 1mo ago Changed · +3 lines 7a7feb5c1c21
- 2mo ago Changed · +12 lines 36c2275fcd98
- 2mo ago Changed · +53 lines 271041ce79fe
- 2mo ago First seen · 233 lines · 64 tokens per session scan A c581a3c86135
develop-wework-plugin is a skill published in the GitHub repository wecode-ai/Wegent (885 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 3,112 once invoked, about $0.0003 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 2026-09-03.
develop-wework-plugin compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| develop-wework-pluginwecode-ai/Wegent | Skill | 885 | today | Apache-2.0 | A | 64 | Claude Code, Codex |
| article-writernetease-youdao/LobsterAI | Skill | 6.2k | today | MIT | A | 62 | Claude Code, Codex |
| skin-creatornetease-youdao/LobsterAI | Skill | 6.2k | today | MIT | A | 48 | Claude Code, Codex |
| content-plannernetease-youdao/LobsterAI | Skill | 6.2k | today | MIT | A | 63 | Claude Code, Codex |
| skill-vetternetease-youdao/LobsterAI | Skill | 6.2k | today | MIT | A | 42 | Claude Code, Codex |
| stock-analyzernetease-youdao/LobsterAI | Skill | 6.2k | today | MIT | A | 53 | Claude Code, Codex |
| weathernetease-youdao/LobsterAI | Skill | 6.2k | today | MIT | A | 13 | Claude Code, Codex |