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/aidotnet/opencowork/create-extensionnpx skills add AIDotNet/OpenCowork --skill create-extensiongit clone --depth 1 https://github.com/AIDotNet/OpenCoworkWrote 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/aidotnet/opencowork/create-extension)<a href="https://agentmods.dev/skills/aidotnet/opencowork/create-extension"><img src="https://agentmods.dev/badge/skills/aidotnet/opencowork/create-extension.svg" alt="Measured on agentmods" 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 | $0.00082 | $0.00685 |
| Opus 5 | $0.00041 | $0.00342 |
| Sonnet 5 | $0.00016 | $0.00137 |
| Haiku 4.5 | $0.00008 | $0.00068 |
Grade A, and why
create-extension 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 5d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Extension
Create OpenCowork Custom Extensions, not App plugins or message channel plugins.
Before creating or changing an extension, read references/extension-v1.md. When the extension
should also bundle skills, sub-agents, slash commands, MCP servers, or persistent state,
additionally read references/extension.md.
Workflow
- Confirm the extension is an OpenCowork Custom Extension: a local folder installed from
Settings -> Extensions with an
extension.jsonmanifest. - Choose the smallest template:
minimal: declarative HTTP demo tool.http: declarative HTTP tool for a specific endpoint.js: sandboxed JavaScript handler tool.
- Scaffold with the bundled script, then customize the generated files.
- Validate the generated extension with the same script before handoff.
- Tell the user to install the folder from Settings -> Extensions, enable it, and start a new chat request so dynamic tools refresh.
Scaffold
Run from any working directory, using the absolute path to this skill's script:
python3 {skill_root}/scripts/create_extension.py my_extension --path /absolute/output/dir --template minimal
Useful variants:
python3 {skill_root}/scripts/create_extension.py company_search \
--path /absolute/output/dir \
--template http \
--url "https://api.example.com/search?q={{input.query}}"
python3 {skill_root}/scripts/create_extension.py local_summary \
--path /absolute/output/dir \
--template js
--path is the parent directory where the extension folder is created. The script creates
<path>/<extension-id>/.
Use --force only when intentionally replacing an existing generated folder.
Editing Guidance
- Keep
extension.jsonas the single declaration entry. - Match the folder name and manifest
id. - Use declarative HTTP tools when possible. Use JavaScript handlers when the extension needs local composition, storage, custom result shaping, or multiple host-mediated requests.
- Declare every network origin used by HTTP tools in
permissions.network. - JavaScript handlers must use
ctx.fetchfor network access; directfetch, Node imports, Electron, filesystem, and shell access are unavailable. - Put secrets in
configSchemafields with"type": "secret"and reference them with{{config.key}}. - Set
readOnly: trueonly for pure read tools. Non-GET HTTP tools require approval unless explicitly read-only.
What ships with it
2 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.
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.
- 5d ago First seen · 78 lines · 82 tokens per session scan A b37558752417
create-extension is a skill published in the GitHub repository AIDotNet/OpenCowork (634 stars, last pushed 2d ago), licensed Apache-2.0. It adds 82 tokens to every session and 685 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…