Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/wecode-ai/Wegentnpx agentmods add skills/wecode-ai/wegent/plugin-creatorWrote 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/plugin-creator)<a href="https://agentmods.dev/skills/wecode-ai/wegent/plugin-creator"><img src="https://agentmods.dev/badge/skills/wecode-ai/wegent/plugin-creator/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/plugin-creator"><img src="https://agentmods.dev/badge/skills/wecode-ai/wegent/plugin-creator.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 | $0.00046 | $0.00795 |
| Opus 5.5 | $0.00018 | $0.00318 |
| Sonnet 5.5 | $0.00009 | $0.00159 |
| Haiku 4.5 | $0.00005 | $0.00080 |
Grade A, and why
wework-plugin-creator 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 4d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wework Plugin Creator
Use the installed Codex plugin-creator skill for common plugin structure,
metadata, skills, and marketplace helpers. Apply the Wework workflow below to
storage, authentication, and validation. This skill and its authentication SDK
are shipped by the Executor and work without a Wegent source checkout.
Choose the authentication path
Before generating a plugin, establish how its business commands authenticate:
- Public data or a skill without authenticated commands: do not add Connectors.
- An existing platform-managed remote Connector/MCP: reuse that connection; do not export platform credentials or wrap it in a local account adapter.
- A plugin-owned local CLI/session, password, API token, or OAuth authorization that must work on cloud devices: read references/account-auth.md, generate the adapter using the bundled SDK, and route business calls through that SDK.
connectors and localAuth alone do not enable account synchronization. Each
supported local credential flow needs connectors[].accountAuth, a working
provider implementation, and a delegated business entrypoint. If the provider
cannot safely support this, explain the concrete limitation; do not advertise
cloud authentication support or invent credential copying.
Create and iterate
- Resolve the source location from the task environment. For
DEVICE_TYPE=cloud, use$WEGENT_TASK_WORKSPACE/plugins/<plugin-name>. Otherwise resolve the registeredwework-personalmarketplace and use its existing plugin directory. Do not use upstream defaults under~/pluginsor~/.agents. - For native account authentication, use
scripts/auth-sdk/tool.py scaffoldas described in the reference. For other plugins, use the upstream scaffold with the explicit destination. Preserve existing source and manifest fields when extending a plugin; scaffold into a temporary directory to obtain templates. - Implement the requested skills/MCP/business commands. Keep the existing native Connector login entry; authentication setup remains a host operation, and cloud tasks must never request passwords, tokens, or exported credentials.
- Run the Wework validator below, then test provider behavior with synthetic credentials and the unpacked distributable. A scaffold passing validation does not mean its provider is implemented or authenticated.
- Locally, keep both managed marketplace manifests consistent and install/update
through the existing managed marketplace flow. In cloud tasks, leave the source
in the Task workspace and run
plugin-workspace describewith the Executor. Return the complete[WEGENT_PLUGIN_RESULT]line verbatim. Publish only when requested, using the same source and the host's publication workflow.
What ships with it
7 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.
- references/account-auth.en.md 3.4 KB
- references/account-auth.md 5.8 KB
- scripts/codex-plugin-creator/README.md 408 B
- scripts/codex-plugin-creator/scripts/identifier_validation.py 784 B runs code
- scripts/codex-plugin-creator/scripts/validate_plugin.py 21 KB runs code
- scripts/validate_wework_plugin.py 8.8 KB runs code
- tests/test_validation.py 6.1 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.
- 4d ago Changed caeb89f5360a
- 1mo ago First seen · 74 lines · 46 tokens per session scan A d41a6089682f
wework-plugin-creator is a skill published in the GitHub repository wecode-ai/Wegent (872 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 795 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 2026-09-10.
Other skills, from other repositories
article-writer
Multi-style article creation skill. Supports 5 writing styles (deep analysis, practical guide, story-driven, opinion, news brief), including complete workflow: material collection → outline → content → formatting. Activated when users mention "write article", "write post", "create", or "draft".
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
skin-creator
Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skinpack workflow marker; do not use for ordinary theme or image requests.
content-planner
WeChat Official Account topic planning and content calendar management. Based on WeChat article search and trending analysis, generates differentiated topic recommendations and outputs structured content calendars. Activated when users mention "topic", "planning", "content calendar", "trending", or "what to write next…
music-search
Search cloud drives for downloadable music resources (songs, albums, lossless audio). Use this skill when the user wants to download a specific song or album. Do NOT use for general music information, lyrics, or recommendations.
skill-vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.