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-project-context-packgit 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-project-context-pack)<a href="https://agentmods.dev/skills/okhp3/skillz/okhp3-cowork-project-context-pack"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-cowork-project-context-pack/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-project-context-pack"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-cowork-project-context-pack.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 | $0.00061 | $0.01162 |
| Opus 5 | $0.00030 | $0.00581 |
| Sonnet 5 | $0.00012 | $0.00232 |
| Haiku 4.5 | $0.00006 | $0.00116 |
Grade A, and why
okhp3-cowork-project-context-pack 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
okhp3-cowork-project-context-pack
OverKill Hill P³ · overkillhill.com · github.com/OKHP3
Compress approved project evidence into a usable brief without making the brief look more certain or complete than its sources allow.
Scope
| In scope | Out of scope |
|---|---|
| A selected project, time window, sources, and a reviewable context brief | Broad tenant discovery, sharing, changing files, or treating access as universal |
Host contract
- Target: Microsoft Copilot Cowork personal custom skill.
- Portable core: synthesize named files, messages, decisions, and meeting records into a brief with a source ledger.
- Cowork adaptation: selected OneDrive, SharePoint, email, and meeting context may be attached or accessed only under current user permissions.
- Evidence: documented Cowork context behavior; no live package run.
Activation boundary and handoff
- Interactive and automation boundary: Use interactively by default. A scheduled or event-driven run may produce a draft only; it must not send, post, schedule, share, create, modify, move, rename, or delete anything.
- Approval policy: Require a current-session, target- and content-specific confirmation before an external action. This is this skill's policy, not a claim that Cowork enforces the same granularity.
- Portable fallback: Outside verified Cowork retrieval, use only material
supplied or attached by the user. Otherwise return
NEEDS INPUT; do not search local, tenant, or connector context. - Host availability: Cowork custom skills are not supported on mobile.
Return
NOT SUPPORTEDon an unavailable surface. A handoff guides work after activation; it cannot prove exclusive host skill selection. - Handoff: Use research evidence log for claim-level research and stakeholder update for communications derived from the selected context.
Required input and safe outcomes
Confirm the project identity, audience, decision purpose, source boundaries,
and freshness window. Return NEEDS INPUT for an unclear project or source
scope, INSUFFICIENT PERMISSION for unavailable files or conversations, and
NOT SUPPORTED when the host cannot retrieve the chosen source type.
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.
- 7d ago First seen · 112 lines · 61 tokens per session scan A e20529736801
okhp3-cowork-project-context-pack is a skill published in the GitHub repository OKHP3/skillz (3 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 1,162 once invoked, about $0.0003 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
pm-brainstorm
A guided brainstorming workflow for exploring a new product idea before detailed research or requirements work. It collects basic information about the product, users, and problem through staged questions.
start-super-pm
Use when starting any product management task - automatically detects task type and invokes appropriate PM skill using intelligent routing.
pm-priority
A Chinese-language procedure for ranking several product requests when time or resources are limited. It supports scoring or grouping methods such as RICE, KANO, and MoSCoW to decide what should be done first.
pm-change
A requirements-change workflow for recording a proposed change, assessing its effects, and deciding whether to approve it.
pm-cross
A Chinese-language planning workflow for coordinating work between departments such as product, engineering, design, testing, operations, and legal.
pm-risk
A structured process for identifying, rating, responding to, and monitoring project risks before important delivery points or launch.