okhp3-cowork-skill-foundry

okhp3-cowork-skill-foundry is a skill for Claude Code, Codex from OKHP3/skillz. It costs 80 tokens per session (1,899 once invoked), scanned A, original, MIT.

A design and packaging workflow for creating a task-focused skill for Microsoft Copilot Cowork, a Microsoft 365 work assistant. It helps turn a repeatable personal workflow into documented instructions or an app package.

In plain words
What is it for?
Use it to author skills for draft-only email, meeting, file, research, or work-queue workflows. It is not for SharePoint site skills, Copilot Studio agents, or GitHub repository skills.
Why use it?
It provides a defined scope, delivery format, safety boundary, and evaluation process for a new skill.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to author skills for draft-only email, meeting, file, research, or work-queue workflows. It is not for SharePoint site skills, Copilot Studio agents, or GitHub repository skills.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/okhp3/skillz/okhp3-cowork-skill-foundry
View source ↗ OKHP3/skillz
Install

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.

Any agent
npx skills add OKHP3/skillz --skill okhp3-cowork-skill-foundry
Clone the repo
git clone --depth 1 https://github.com/OKHP3/skillz

Made for: Claude Code, Codex.

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 okhp3-cowork-skill-foundry

README.md
[![agentmods](https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-cowork-skill-foundry/github.svg)](https://agentmods.dev/skills/okhp3/skillz/okhp3-cowork-skill-foundry)
Your own site
<a href="https://agentmods.dev/skills/okhp3/skillz/okhp3-cowork-skill-foundry"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-cowork-skill-foundry/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 okhp3-cowork-skill-foundry

Your own site · 80×15
<a href="https://agentmods.dev/skills/okhp3/skillz/okhp3-cowork-skill-foundry"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-cowork-skill-foundry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,899 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 $0.00080 $0.01899
Opus 5 $0.00040 $0.00949
Sonnet 5 $0.00016 $0.00380
Haiku 4.5 $0.00008 $0.00190

Measured 7d ago against content hash 0c622a8d5cd8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

okhp3-cowork-skill-foundry 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 7d 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.

copilot/okhp3-cowork-skill-foundry/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

okhp3-cowork-skill-foundry

OverKill Hill P3 · overkillhill.com · github.com/OKHP3

Create a compact, personal-workflow skill for Microsoft Copilot Cowork. This Foundry is the host adapter above the portable Agent Skills baseline: it makes the Cowork package, Microsoft 365 context, and sensitive-action boundary explicit.

Scope

In scope Out of scope
A bounded, repeatable Cowork task using available Microsoft 365 context A site-owned SharePoint skill, a Copilot Studio agent capability, or a GitHub repository skill
Draft-only email, meeting, file, research, or work-queue workflows Sending, deleting, sharing, publishing, or changing records without current-session approval
A skills-only package or a handoff for an M365 app package Building an MCP connector, registering OAuth, or submitting an app without authorization

Host contract

  • Target: Microsoft Copilot Cowork.
  • Delivery mode: select exactly one before authoring: personal OneDrive skill, uploaded skill/archive, or M365 app-package plugin. These have different roots, validation, sharing, and test paths.
  • Portable syntax is not enough: Cowork-specific discovery, Microsoft 365 context, manifest entries, tenant policy, and action approval must be tested separately from the Markdown contract.
  • Do not assume a connector: a skills-only package is valid. If the task needs an external system, declare that as a separately authorized connector dependency rather than pretending the skill supplies it.
  • Read references/cowork-host-contract.md before choosing a packaging path or writing the host boundary.

Foundry workflow

  1. Capture one real repeated task: trigger phrases, desired result, correction history, input examples, unavailable context, and the moment a user must approve an effect. Reject a vague "help with my work" request.
  2. Choose a delivery mode before writing host instructions:

Read the full file on GitHub · 164 lines

Files

What ships with it

3 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. 7d ago First seen · 164 lines · 80 tokens per session scan A 0c622a8d5cd8

Subscribe to this mod's changes

okhp3-cowork-skill-foundry is a skill published in the GitHub repository OKHP3/skillz (3 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 1,899 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 2026-09-03.