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 project-health-checkgit 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/project-health-check)<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/project-health-check"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/project-health-check/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/project-health-check"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/project-health-check.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 | $0.00058 | $0.04481 |
| Opus 5.5 | $0.00023 | $0.01792 |
| Sonnet 5.5 | $0.00012 | $0.00896 |
| Haiku 4.5 | $0.00006 | $0.00448 |
Grade A, and why
project-health-check 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 24d 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 — 520 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Health Check
Purpose
Assess the current health of a project from the SharePoint content available to the user. Review project documents and, when available, structured SharePoint lists such as milestones, risks, actions, decisions, and deliverables.
The skill must produce an evidence-based health assessment. Never invent project facts, dates, owners, statuses, or missing documents.
Before Starting
- Determine the project scope from the user's selection, current SharePoint location, or prompt.
- Use the selected files and relevant project content available on the current SharePoint site.
- Prefer current, authoritative project artifacts over older drafts.
- If several project areas are present and the intended project is ambiguous, ask the user which project to assess.
- If a project reporting date is explicitly provided, use it. Otherwise use the current date.
- Do not require every source type below. Work with the information that is available and report coverage gaps.
Preferred Sources
Look for evidence in these source types when available:
- Project charter, project brief, or initiation document
- Current status report
- Milestone or project plan
- Risk register
- Action / issue register
- Decision register
- Deliverables or document register
- Meeting minutes and steering committee notes
- Other project documents that contain dates, commitments, blockers, owners, or decisions
Structured lists should be treated as primary sources for the facts they own. For example, use a Risk Register for risk status when one is available rather than inferring all risks from narrative documents.
Output Structure
Produce the result in this order.
1. Project Health
State one overall status:
- GREEN — project is broadly on track; no material issue needs management attention.
- AMBER — one or more material concerns require attention, but recovery appears achievable.
- RED — a critical condition threatens delivery or requires immediate management action.
- UNKNOWN — available evidence is insufficient for a reliable health assessment.
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.
- 24d ago First seen · 520 lines · 58 tokens per session scan A 7bf3083ef9ec
project-health-check is a skill published in the GitHub repository pnp/sharepoint-skills (137 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 4,481 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-23.
Other skills, from other repositories
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
flow-parallel
Decompose and execute large changes, migrations, or multi-issue fixes in parallel with quality gates.
skill-task-management
Manage tasks with Claude Code native tools — use to track TODOs, delegate work, and monitor progress.
skill-issues
Track project blockers, bugs, and gaps across sessions — use when issues pile up or need triage.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
skill-work-slicing
Break a plan or spec into vertical slices that each declare what blocks them — use when work is agreed but not yet cut into fileable pieces.