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npx skills add pnp/sharepoint-skills --skill unpublished-content-reportgit clone --depth 1 https://github.com/pnp/sharepoint-skillsWrote this?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[](https://agentmods.dev/skills/pnp/sharepoint-skills/unpublished-content-report)<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/unpublished-content-report"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/unpublished-content-report/github.svg" alt="Measured on agentmods" height="20"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a href="https://agentmods.dev/skills/pnp/sharepoint-skills/unpublished-content-report"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/unpublished-content-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00115 | $0.01019 |
| Opus 5 | $0.00057 | $0.00509 |
| Sonnet 5 | $0.00023 | $0.00204 |
| Haiku 4.5 | $0.00012 | $0.00102 |
Grade A, and why
unpublished-content-report scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation,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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unpublished content report
When to use
Use this skill when the user wants an HTML governance report covering SharePoint documents and site pages that aren't published and haven't been edited for a specified period. Use it for stale drafts, pending/rejected content, checked-out pages, or unpublished changes. The report must sort by days since last edit in descending order and be saved in a document library.
Inputs
- Current SharePoint site URL and context.
- Inactivity threshold in days. Default to 14 only when the user doesn't provide one.
- Destination document library. Default to
Reportsonly when the user doesn't provide one. - Optional report filename. Otherwise use
Unpublished-content-inactive-<days>-days.html. - Scope is documents in user-facing document libraries plus pages in the site's Site Pages library. Exclude system, asset, style, preservation, template, report, and
AgentAssetslibraries unless the user includes them.
Steps
- Get the current date/time before calculating relative ages.
- Discover the site's lists and libraries, including the Site Pages library. Identify user-facing document libraries and exclude system libraries.
- Verify the destination library exists. If it doesn't, create it as a document library with a clear report-oriented description.
- Retrieve schemas before querying items. Identify these internal fields where available:
FileLeafRef,FileRef,Modified,Editor,_ModerationStatus,_UIVersionString,CheckoutUser, and page fields such asTitle,FirstPublishedDate, andPromotedState. - Query all files recursively with a row limit equal to the known item count, or 50,000 when unknown. Retrieve the complete dataset before filtering.
- Determine publication state from SharePoint metadata rather than filenames:
- In moderated libraries, treat
_ModerationStatusvalues equivalent to Approved/Published as published. Pending, Draft, Rejected, or other non-approved values are unpublished. - In versioned libraries, a version ending in
.0is a published major version. A version ending in a non-zero minor number indicates draft or unpublished changes. - Treat checkout-only pages, never-published pages, and pages with draft changes as unpublished.
- Don't classify an item as unpublished solely because the library doesn't use moderation or minor versions. If no reliable publication-state signal exists, omit the item and note the skipped library in the report.
- In moderated libraries, treat
- Calculate whole days since
Modified. Keep items whose age is greater than or equal to the requested threshold. - Normalize each match with item name and link, type, library, publication state, version, last edited date/time, editor, and days since last edit.
- Sort by days since last edit descending, then item name ascending as a stable tie-breaker.
- Build the HTML using
Report.htmland, when practical,LiveData.htmlso results refresh from source libraries when opened. Pass every source list identity to the live-data tool; don't hand-write REST or Graph calls. - Include summary cards for total items, documents, and pages; a concise criteria note; and a table containing all matching items. Escape user-controlled values before inserting them into raw HTML.
- Route generated HTML through an output data reference, then create the
.htmlfile in the destination library using that reference. Don't reconstruct content from a truncated preview. - Verify the file was created and return a link. If any tool fails or data is incomplete, say so plainly and don't invent results.
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 · 58 lines · 115 tokens per session scan A 4992296cabbe
unpublished-content-report is a skill published in the GitHub repository pnp/sharepoint-skills (118 stars, last pushed 3d ago), licensed MIT. It adds 115 tokens to every session and 1,019 once invoked, about $0.0006 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
project-status-tracker
Maintains living project files (project.md, decisions.md, risks.md, links.md) in a per-project OneDrive folder from emails, Teams channels and meeting transcripts, and generates a weekly DRAFT status document in Word. Use when the user asks to set up tracking for a project, update a project's status files, log a…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
flow-parallel
Decompose and execute large changes, migrations, or multi-issue fixes in parallel with quality gates.
skill-issues
Track project blockers, bugs, and gaps across sessions — use when issues pile up or need triage.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.