news-governance-review

news-governance-review is a skill for Claude Code, Codex from pnp/sharepoint-skills. It costs 211 tokens per session (4,487 once invoked), scanned A, original, MIT.

A read-only review of news posts in a SharePoint intranet, an internal company website. It checks whether posts are current, complete, relevant, well targeted, findable, and assigned to an owner.

In plain words
What is it for?
Use it to audit Site Pages or intranet news, identify posts that need keeping, updating, archiving, unpublishing, or deletion, and view the recommendations in an HTML dashboard.
Why use it?
Older, unfinished, or ownerless news can crowd out important updates. The review creates a prioritised cleanup list without changing or deleting any content.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to audit Site Pages or intranet news, identify posts that need keeping, updating, archiving, unpublishing, or deletion, and view the recommendations in an HTML dashboard.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pnp/sharepoint-skills/news-governance-review
Install

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.

Any agent
npx skills add pnp/sharepoint-skills --skill news-governance-review
Clone the repo
git clone --depth 1 https://github.com/pnp/sharepoint-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for news-governance-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/pnp/sharepoint-skills/news-governance-review/github.svg)](https://agentmods.dev/skills/pnp/sharepoint-skills/news-governance-review)
Your own site
<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/news-governance-review"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/news-governance-review/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.

agentmods 80×15 button for news-governance-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/news-governance-review"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/news-governance-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 211 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,487 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00211 $0.04487
Opus 5 $0.00105 $0.02243
Sonnet 5 $0.00042 $0.00897
Haiku 4.5 $0.00021 $0.00449

Measured 13d ago against content hash 16c7e7b2dd1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

news-governance-review 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 13d 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.

Skills/news-governance-review/news-governance-review/SKILL.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

News Governance Review

Purpose

Intranet news flows fill up over time with posts that are outdated, half-finished, mistargeted, or ownerless, and important news gets pushed down and missed. This skill gives site owners, editors, and communications teams a structured governance review of the news on a site.

It evaluates each news post against freshness, publication-quality, governance, findability, relevance, and link quality, assigns a recommended outcome with reasons, and produces a color-coded HTML dashboard that works directly as a cleanup backlog. It relies only on the default Site Pages fields available on every modern SharePoint site; no custom columns are required.

It is strictly advisory and read-only: it reads pages and metadata, but never deletes, unpublishes, archives, edits, or reclassifies anything. Every decision to keep, update, archive, unpublish, or delete stays with a human content owner.

Trigger Phrases

Activate this skill when the user says any of the following (or close variations):

  • "review news" / "review our news posts" / "news review report"
  • "news governance" / "audit news posts"
  • "check news quality" / "find outdated news"
  • "clean up intranet news" / "news cleanup backlog"
  • "which news posts are obsolete"

Inputs & Scope

Determine the review scope from the user's request and the current context, in this order:

  1. Selected pages: if the user has news posts/pages selected or says "these/this", review exactly the selection.
  2. Named site or library: if the user names a site or a pages library (e.g., "review the news on the HR site"), resolve it and review its news posts.
  3. Current site's news: if no other scope is given, review the news posts in the current site's Site Pages library.
  4. If no scope can be resolved, ask the user which site, library, or pages to review. Do not guess.

What counts as a news post: pages in the Site Pages library whose PromotedState is 2 (promoted as news). If the user explicitly asks to include all site pages, widen the scope and say so in the report. If PromotedState is unavailable, fall back to reviewing all pages in the resolved library and record that in the report's limitations section.

Read the full file on GitHub · 266 lines

Changes

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.

  1. 13d ago First seen · 266 lines · 211 tokens per session scan A 16c7e7b2dd1f

Subscribe to this mod's changes

news-governance-review is a skill published in the GitHub repository pnp/sharepoint-skills (118 stars, last pushed 4d ago), licensed MIT. It adds 211 tokens to every session and 4,487 once invoked, about $0.0011 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 2026-08-30.