agentmods.dev

copilot-cowork-plugin

copilot-cowork-plugin is a skill for Claude Code from Yesterday-AI/skills. It costs 82 tokens per session (1,837 once invoked), scanned A, original, MIT.

A packaging tool for converting an existing agent skill into a Microsoft 365 Copilot Cowork app package. It builds the required manifest and ZIP package, converts some text files when requested, and checks the package before upload.

In plain words
What is it for?
Use it to build and validate a package from a local SKILL.md folder, set package details and icons, exclude non-portable files, and handle some unknown text-file extensions. It does not create new skills or package binary files such as PDFs.
Why use it?
Microsoft 365 Copilot Cowork expects an app package rather than a local skill folder. This tool avoids hand-writing the package steps and catches unsupported or missing files before deployment.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 validate_package.py ./output/mein-skill-cowork.zip.

Part of the copilot-cowork-plugin plugin — 1 skill shipped together

not rated 2repo 1mo ago A scan 82 tokens original MIT

Good fit Use it to build and validate a package from a local SKILL.md folder, set package details and icons, exclude non-portable files, and handle some unknown text-file extensions. It does not create new skills or package binary files such as PDFs.

Compare 6 skills from other repositories ↓
View source ↗ Yesterday-AI/skills
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Yesterday-AI/skills
agentmods
npx agentmods add skills/yesterday-ai/skills/copilot-cowork-plugin

Made for: Claude Code.

Or install copilot-cowork-plugin, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for copilot-cowork-plugin

README.md
[![agentmods](https://agentmods.dev/badge/skills/yesterday-ai/skills/copilot-cowork-plugin/github.svg)](https://agentmods.dev/skills/yesterday-ai/skills/copilot-cowork-plugin)
Your own site
<a href="https://agentmods.dev/skills/yesterday-ai/skills/copilot-cowork-plugin"><img src="https://agentmods.dev/badge/skills/yesterday-ai/skills/copilot-cowork-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.

agentmods 80×15 button for copilot-cowork-plugin

Your own site · 80×15
<a href="https://agentmods.dev/skills/yesterday-ai/skills/copilot-cowork-plugin"><img src="https://agentmods.dev/badge/skills/yesterday-ai/skills/copilot-cowork-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,837 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00082 $0.01837
Opus 5.5 $0.00033 $0.00735
Sonnet 5.5 $0.00016 $0.00367
Haiku 4.5 $0.00008 $0.00184

Measured 1mo ago against content hash dd2406f1c443, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

copilot-cowork-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.

The scan reads SKILL.md. This mod also ships 2 executable files (build_package.py, validate_package.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.compiled/skill-plugins/copilot-cowork-plugin/skills/copilot-cowork-plugin/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Cowork Plugin — Skills nach Microsoft 365 bringen

Microsoft 365 Copilot Cowork frisst keine Skill-Ordner, sondern M365-App-Pakete („MOS-Paket"). Ein Skill ist kein Plugin: Ohne manifest.json auf ZIP-Wurzelebene lautet die Antwort immer „Dies sieht nicht wie ein unterstütztes Plug-In aus."

Die beiden CLIs in diesem Ordner erledigen Bau und Prüfung. Schreib die Schritte nie von Hand nach — die Fallstricke stecken in den Skripten.

Ablauf

python3 build_package.py ./mein-skill --out ./output \
  --publisher "Example Publisher" --website https://example.com \
  --privacy https://example.com/privacy --terms https://example.com/terms
python3 validate_package.py ./output/mein-skill-cowork.zip

Erst hochladen, wenn der Validator 0 Fehler meldet. Warnungen sind Absicht: sie markieren Dateiendungen, deren Zulässigkeit noch niemand nachgewiesen hat.

Nützliche Flags: --exclude 'agents/*' wirft nicht portierbare Teile raus, --convert-unknown wandelt auch unbelegte Endungen in .md (nur Textdateien; Binärdateien wie .pdf oder .woff2 bricht der Build mit Hinweis ab, dann --exclude), --package-name, --version, --icon-color/-outline überschreiben die Defaults. Eigene Icons müssen PNGs mit 192×192 (color) bzw. 32×32 (outline) Pixeln sein, --app-id eine GUID; beides prüfen Builder und Validator. Mehrere Skill-Ordner in einem Aufruf ergeben ein Paket (max. 20).

Zu viele Companion-Dateien? Das Limit von 20 ist die häufigste harte Grenze bei gewachsenen Skills. --bundle 'kit/components/*' fasst jedes passende Verzeichnis zu einer .md zusammen — Markdown direkt, Code als Codeblock, Verweise darauf werden mitgezogen. Der Agent liest ein Bündel genauso gut, hat sogar alle Teile auf einmal. Gebündelt wird nur Text: liegt ein Bild oder eine andere Binärdatei im Verzeichnis, bricht der Build mit Hinweis ab — die Datei per --exclude ausschließen oder das Verzeichnis nicht bündeln.

Manual-only Skills (disable-model-invocation: true) werden standardmäßig gestoppt; false gilt nicht als manual-only. Erst nach Prüfung ihrer Seiteneffekte darf --allow-auto-invocation die entsprechende Frontmatter-Einschränkung entfernen. Eine Formatkonvertierung erteilt keine neue Ausführungsbefugnis.

Read the full file on GitHub · 131 lines

Files

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.

Changes

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.

  1. 1mo ago First seen · 131 lines · 82 tokens per session scan A dd2406f1c443

Subscribe to this mod's changes

copilot-cowork-plugin is a skill published in the GitHub repository Yesterday-AI/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 1,837 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 2026-10-14.

Building agentsagent-skillsai-agentsclaude-code-pluginscursorcursor-plugins
Related

copilot-cowork-plugin compared with skills from other repositories

copilot-cowork-plugin next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
copilot-cowork-pluginYesterday-AI/skillsSkill21mo agoMITA82Claude Code
render-3d-product-showcasegooseworks-ai/goose-skillsSkill1.3k6d agoMITA159Claude Code, Codex
render-airdrop-carouselgooseworks-ai/goose-skillsSkill1.3k6d agoMITA207Claude Code, Codex
email-lifecycle-flow-writergooseworks-ai/goose-skillsSkill1.3k6d agoMITA50Claude Code, Codex
work-with-creators-creator-vettinggooseworks-ai/goose-skillsSkill1.3k6d agoMITA110Claude Code, Codex
Accessibility Manual AuditPramodDutta/qaskillsSkill24810d agoMITA36Claude Code, Codex
loop-engineeringhuytieu/COG-second-brainSkill1.4k21d agoMITA63Claude Code