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-sharepoint-library-intake-classifiergit 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-sharepoint-library-intake-classifier)<a href="https://agentmods.dev/skills/okhp3/skillz/okhp3-sharepoint-library-intake-classifier"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-sharepoint-library-intake-classifier/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-sharepoint-library-intake-classifier"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-sharepoint-library-intake-classifier.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 | $0.00055 | $0.01093 |
| Opus 5 | $0.00028 | $0.00547 |
| Sonnet 5 | $0.00011 | $0.00219 |
| Haiku 4.5 | $0.00006 | $0.00109 |
Grade A, and why
okhp3-sharepoint-library-intake-classifier 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
okhp3-sharepoint-library-intake-classifier
OverKill Hill P³ · overkillhill.com · github.com/OKHP3
Outcome
Return a file-by-file classification draft that maps only to the supplied taxonomy, makes confidence and exceptions visible, and leaves every move or metadata update for human review.
Scope
Use for selected library files with an approved taxonomy and required metadata. This skill recommends classifications; it does not create folders, move files, or apply metadata by default.
Host contract
| Item | Contract |
|---|---|
| Target host | Copilot in SharePoint, preview support status |
| Native surface | Selected library files and accessible metadata |
| Portable core | Taxonomy matching, confidence explanation, exception routing, and review output |
| Host adapter | Reads file content and metadata only when native capability and user permission are available |
| Mutation | Show each proposed classification and require explicit confirmation before any supported change |
| Evidence | Analytical design only; no tenant discovery or classification run has occurred |
Activation evidence preflight
- Confirm the named Library and the selected files or inspection scope required by this task.
- In a real SharePoint test, confirm either explicit invocation of this skill or the SharePoint skill indicator card. The presence of this package alone is not evidence that the host discovered or loaded it.
- If the host cannot load the skill or expose the required Library context,
return
NOT SUPPORTED, identify the missing capability, and do not claim that the review or draft was completed. - Keep the result analytical until a test records the site, user role, input scope, and observed host behavior.
Procedure
- Confirm the target library, selected files, approved taxonomy, required metadata, and whether the user wants a draft only.
- Read only accessible file names, metadata, and content needed for the supplied classification rules. Record unreadable content as a limitation.
- Map each file to a supplied category only when the evidence supports it.
Use
NEEDS INPUTfor missing facts andEXCEPTIONfor no valid category. - Return this review table:
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 · 113 lines · 55 tokens per session scan A a44ac87a5e5d
okhp3-sharepoint-library-intake-classifier is a skill published in the GitHub repository OKHP3/skillz (3 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,093 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
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
baoyu-url-to-markdown
Fetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with site-specific adapters). Built-in adapters for X/Twitter, YouTube transcripts, Hacker News threads, and generic pages via Defuddle. Handles login/CAPTCHA via interaction wait modes. Use when user wants to save a webpage as markdown.
daily-report-generator
Automatically generate daily construction reports from field data, worker inputs, weather, and progress photos. Creates professional PDF reports.
n8n-daily-report
Automate daily construction report generation using n8n workflow automation.
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.
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.