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 OKHP3/skillz --skill okhp3-cowork-skill-foundrygit clone --depth 1 https://github.com/OKHP3/skillzWrote 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/okhp3/skillz/okhp3-cowork-skill-foundry)<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.
<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>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 | $0.00080 | $0.01899 |
| Opus 5 | $0.00040 | $0.00949 |
| Sonnet 5 | $0.00016 | $0.00380 |
| Haiku 4.5 | $0.00008 | $0.00190 |
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.
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
- 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.
- Choose a delivery mode before writing host instructions:
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.
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.
- 7d ago First seen · 164 lines · 80 tokens per session scan A 0c622a8d5cd8
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.
Other skills, from other repositories
vastai-sdk
Vast.ai Python SDK — high-level API for GPU instances, volumes, serverless endpoints, and billing.
pm-aarrr
A post-launch product-growth workflow based on AARRR: acquiring users, activating them, retaining them, earning revenue, and gaining referrals.
pm-docs
A workflow for producing product documents such as PRDs, BRDs, and MRDs. These are structured documents describing what a product needs, its business case, and its market.
product-marketing-copywriter
A marketing-copy tool that analyzes audience problems and product benefits, then creates promotional headlines and body text. Marketing copy is writing intended to explain and promote a product.
baoyu-post-to-wechat
A publishing workflow for WeChat Official Accounts, a platform used to publish articles and media updates in China. It takes Markdown or HTML content and handles formatting and publishing through an API or browser automation.
pm-position
A guided process for defining a product’s market position, value, audience, competitive difference, business model, pricing, and revenue plan. The instructions are written mainly in Chinese.