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-article-curatorgit 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-article-curator)<a href="https://agentmods.dev/skills/okhp3/skillz/okhp3-sharepoint-library-article-curator"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-sharepoint-library-article-curator/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-article-curator"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-sharepoint-library-article-curator.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 | $0.00066 | $0.01209 |
| Opus 5 | $0.00033 | $0.00605 |
| Sonnet 5 | $0.00013 | $0.00242 |
| Haiku 4.5 | $0.00007 | $0.00121 |
Grade A, and why
okhp3-sharepoint-library-article-curator 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 8d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
okhp3-sharepoint-library-article-curator
OverKill Hill P³ · overkillhill.com · github.com/OKHP3
Scope
Create a curation draft for selected or named articles in one SharePoint document library. The draft identifies a candidate title, summary, category, audience, related-content signal, and missing information without changing the source files or library structure.
Host contract
| Item | Contract |
|---|---|
| Target host | Copilot in SharePoint, preview support status |
| Native surface | A named document library and files accessible to the current user |
| Portable core | Article analysis, collection logic, duplicate signaling, and review table |
| Host adapter | Reads selected files and library context only when the native surface supports it |
| Mutation | Draft only. Any metadata update, rename, move, or publication requires an exact proposed-change review and explicit confirmation. |
| Evidence | Analytical package design only. No live SharePoint discovery or file-operation result has run. |
Copilot in SharePoint uses native capabilities available on the site. It cannot execute custom code or connect to external systems, and it cannot expand the current user's permissions.
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 or review scope, intended audience, taxonomy, publication boundary, and whether the result is a draft or a request for a separately confirmed supported update.
- Read the available file content and library metadata. Record files that are inaccessible, unreadable, or outside scope.
- For each in-scope file, create only evidence-supported recommendations for title, summary, topic, audience, and related-content signal. Preserve the existing value when the source does not support a proposed replacement.
- Treat title or subject similarity as
DUPLICATE_CANDIDATE, never as a deletion, merge, or canonical-source decision. - Return this curation draft:
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.
- 8d ago First seen · 119 lines · 66 tokens per session scan A a27e538f00ce
okhp3-sharepoint-library-article-curator is a skill published in the GitHub repository OKHP3/skillz (3 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 1,209 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.
obsidian-markdown
A Markdown writing workflow for Obsidian, a note-taking app that can link notes together. It supports features such as two-way links, callouts, frontmatter, embedded content, and wikilinks.
obsidian-skills-integrated
A skill for writing and editing Obsidian notes while preserving Obsidian-specific formats. Obsidian is a note-taking app that supports links between notes, callouts, databases, and visual canvases.
pptx-generator
A tool that converts JSON data, a structured text format often used by software, into standard .pptx presentation files. It applies layouts and can format charts and tables.
PDF Processing Pro
A PDF-processing workflow for handling forms, extracting tables, and using OCR to turn scanned text into searchable data. It also performs automated data checks using built-in scripts.