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 jnPiyush/AgentX --skill cowork-plugin-creatorgit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/jnpiyush/agentx/cowork-plugin-creator)<a href="https://agentmods.dev/skills/jnpiyush/agentx/cowork-plugin-creator"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/cowork-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/jnpiyush/agentx/cowork-plugin-creator"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/cowork-plugin-creator.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 | $0.00054 | $0.02473 |
| Opus 5.5 | $0.00022 | $0.00989 |
| Sonnet 5.5 | $0.00011 | $0.00495 |
| Haiku 4.5 | $0.00005 | $0.00247 |
Grade A, and why
cowork-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 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cowork Plugin Creator
WHEN: Creating, converting, reviewing, or packaging a Microsoft 365 Copilot Cowork plugin as an M365 app package
.zipthat bundles skills and optional MCP connectors.
When to Use
Use this skill when the user asks to:
- Build a Cowork plugin that bundles several related skills
- Add an MCP connector so Cowork skills can reach an external system
- Produce an upload-ready Microsoft 365 app package for Cowork
- Repair a plugin package that fails upload validation
Use Cowork Skill Creator instead when the deliverable is a single standalone skill archive with no manifest, icons, or connectors.
Prerequisites
- A business capability that resolves to at least one specialized skill, at least one connector, or both
- PowerShell 7 or later for deterministic package validation and zip creation
color.pngat 192x192 pixels andoutline.pngat 32x32 pixels- An HTTPS MCP endpoint and its tool-description file when a connector is required
Rationalization Table
| Rationalization | Reality |
|---|---|
| "One large skill is simpler than several." | Cowork routes on skill descriptions; broad skills collide and misfire. Split by distinct stage, task, or domain. |
| "The manifest can list extra fields for clarity." | The v1.28 schema sets additionalProperties: false; any undocumented field fails upload. |
| "The folder name is cosmetic." | The frontmatter name must match the folder leaf exactly; mismatch is the most common skill failure. |
| "Icons can be any square image." | color.png must be 192x192 and outline.png must be 32x32, and both must match the manifest references. |
| "The connector tool list lives on the server." | Every remoteMcpServer requires mcpToolDescription.file, and that file must ship inside the zip. |
| "Zipping the plugin folder is enough." | A wrapper directory breaks upload. manifest.json must sit at the archive root. |
| "Credentials in the skill make testing easier." | Secrets never belong in the package; use agentConnectors authorization with a vault referenceId. |
| "Every skill folder in the tree gets picked up." | Only folders listed in agentSkills ship as skills. Unregistered stage folders are dead weight in the archive. |
| "The folder name from the source pipeline is fine as-is." | Names must be lowercase kebab-case. BE-sow-generator fails; sow-generator passes. |
| "The skill can install what it needs at runtime." | Author for a managed container: assume no terminal and no package installation. Ship instructions and templates, not setup steps. |
| "Placeholder and repo files must be cleaned up by hand." | The packager drops .gitkeep, version-control metadata, and build caches from both the archive and the companion count. |
What ships with it
4 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.
- 1mo ago Changed 09493b4f10f8
- 1mo ago First seen · 166 lines · 54 tokens per session scan A 3d02c1748ad4
cowork-plugin-creator is a skill published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 54 tokens to every session and 2,473 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 2026-09-03.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.