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-intelligence-root-cause-analysisgit 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-intelligence-root-cause-analysis)<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/project-intelligence-root-cause-analysis"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/project-intelligence-root-cause-analysis.svg" alt="Measured on agentmods" 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 | $0.00122 | $0.03047 |
| Opus 5 | $0.00061 | $0.01523 |
| Sonnet 5 | $0.00024 | $0.00609 |
| Haiku 4.5 | $0.00012 | $0.00305 |
Grade A, and why
project-intelligence-root-cause-analysis 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Root Cause Analysis
Purpose
Take the change log in the Change Events list and produce a complete causal analysis: the root cause, the chain of events that followed from it, the signals that were present but not acted on, and a clear verdict on what could have prevented the outcome. Every finding must be traceable to a specific event number in the list.
Inputs Required
This skill reads from the Change Events list on this SharePoint site, populated by the Change Event Extraction skill. If the list is empty, run Change Event Extraction first.
Step 1 — Apply the Counterfactual Root Cause Test
For each HIGH signal-strength event in the change log, apply the following test:
"If this event had been handled correctly — escalated, change-ordered, validated, or resolved — would the downstream impact events still have occurred?"
Score each candidate event on three dimensions:
| Dimension | Question | Score 1–5 |
|---|---|---|
| Upstream dependency | How many subsequent HIGH/MEDIUM events depend on this event being unresolved? | 5 = many downstream, 1 = isolated |
| Reversibility window | How long after this event was it still possible to take corrective action before the impact became unavoidable? | 5 = long window, 1 = immediate lock-in |
| Documentation availability | Was the information needed to recognise this as a problem present in the record at the time? | 5 = fully documented, 1 = not visible |
The event with the highest combined score is the primary root cause. If two events score equally, prefer the earlier one (earlier failures compound more).
State which event number from the change log is the root cause, and show the scoring table.
Step 2 — Trace the Causal Chain
Starting from the root cause event, trace the forward sequence of events that led to the impact event (the moment the failure became visible or unavoidable).
For each step in the chain:
- Reference the event number from the change log
- State what happened
- State why it followed from the previous step
- Identify whether there was an intervention window at this step — a point at which the chain could still have been broken
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 · 281 lines · 122 tokens per session scan A 2285bb256ddf
project-intelligence-root-cause-analysis is a skill published in the GitHub repository pnp/sharepoint-skills (108 stars, last pushed today), licensed MIT. It adds 122 tokens to every session and 3,047 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 2026-08-30.
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.
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-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.