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 review-councilgit 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/review-council)<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/review-council"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/review-council/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/review-council"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/review-council.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 33 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00000 | $0.03588 |
| Opus 5 | $0.00000 | $0.01794 |
| Sonnet 5 | $0.00000 | $0.00718 |
| Haiku 4.5 | $0.00000 | $0.00359 |
Grade A, and why
review-council 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 12d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Council
A skill that convenes a panel of expert personas to review any document, idea, proposal, or plan — then synthesizes a verdict with specific, actionable feedback.
This is not a proofreader. The Council exists to surface what the author can't see: blind spots, unstated assumptions, structural weaknesses, audience misalignment, and missed opportunities. It works on anything from a polished board deck to a half-formed idea spoken aloud.
When to Use
Trigger this skill when the user:
- Uploads a file (.docx, .xlsx, .pptx, .pdf) and asks for feedback, review, or critique
- Pastes text and asks "what do you think" or "poke holes in this"
- Describes an idea verbally and wants it stress-tested
- Says "convene the council," "panel review," or "red team this"
- Asks "what am I missing" or "would this work"
- Wants feedback before sharing something with stakeholders, leadership, a board, investors, or the public
Step 1 — Determine the Input
The Council reviews anything. Identify what the user is presenting:
SharePoint artefact in context: If the user is on a SharePoint page, news post, or document library with a file open / selected, take that as the input by default and confirm in one short line ("Reviewing Q3 Strategy.docx in the Strategy library — continue?"). The Council reads:
- Library files (
.docx,.xlsx,.pptx,.pdf) — read via the appropriate file tool. - SharePoint pages and news posts — read the page's text content, title, and section structure.
- List items — review the title, description / rich-text fields, and any attached files. State which fields are being reviewed.
Uploaded file: Read the file using the appropriate method for its type. For .docx, .xlsx, .pptx, or .pdf, read the file contents before proceeding. For spreadsheets, understand the data structure, formulas, and what story the data tells. For decks, evaluate both the narrative arc and individual slide content. For documents, read the full text.
What ships with it
1 file 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.
- 12d ago First seen · 212 lines · 0 tokens per session scan A f01d7cc731c6
review-council is a skill published in the GitHub repository pnp/sharepoint-skills (116 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,588 tokens. 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.
Other skills, from other repositories
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
skill-writing-plans
Create zero-context implementation plans with bite-sized tasks — use for multi-step feature planning.
skill-copilot-provider
GitHub Copilot CLI as optional zero-cost provider via copilot -p programmatic mode.
bf-to-agents-sdk-dotnet-migration
Use when migrating a Bot Framework .NET SDK bot to Microsoft 365 Agents SDK. Triggered by projects that depend on packages: Microsoft.Bot.Builder or Microsoft.Bot.Builder.Integration.AspNet.Core that want to migrate to Agents SDK.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.