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 list-stylinggit 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/list-styling)<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/list-styling"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/list-styling/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/list-styling"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/list-styling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Prompt Injection · line 111 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
- medium Excessive Agency · line 123 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 | $0.00085 | $0.03411 |
| Opus 5 | $0.00043 | $0.01706 |
| Sonnet 5 | $0.00017 | $0.00682 |
| Haiku 4.5 | $0.00009 | $0.00341 |
Grade B, and why
list-styling scanned grade B with 1 finding 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 9d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
**Never apply formatting to the default view, and never tell the user to skip this step.** A broken `rowFormatter` makes a list look empty and is a frightening experience for anyone who isn't a developer. How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
List Styling Engine
Transform SharePoint lists and document libraries into fully art-directed views. This is not a color palette swap — it's a complete visual redesign using every formatting capability SharePoint provides.
The bar: "I can't believe that's SharePoint."
Formatting Capabilities — Use ALL of These
SharePoint provides four levels of formatting. A properly styled view uses MULTIPLE levels together. Do not stop at column formatting.
Level 1: Column Formatting
Per-column rendering. Controls how individual cell values display.
- Status badges, progress bars, date compositions
- Applied via: Column header → Column settings → Format this column → Advanced mode
Level 2: View Formatting (additionalRowClass)
Adds CSS classes to existing rows. Lightweight — doesn't change layout.
- Alternating row colors, conditional row highlighting (overdue tinting)
- Applied via: View dropdown → Format current view → Advanced mode
Level 3: Row Template (rowFormatter)
REPLACES the entire row layout. This is the power move. Instead of SharePoint's default column grid, you define the complete HTML structure of each row.
- Full card layouts with sidebars, composed metadata, multi-section rows
- Can combine multiple columns into a single visual composition
- Applied via: View dropdown → Format current view → Advanced mode (uses
rowFormatterkey instead ofadditionalRowClass)
Level 4: Tile Formatting
Gallery/card view layouts. Each item renders as a card instead of a row.
- Standalone card designs with headers, bodies, footers, progress indicators
- Applied via: Gallery view → Format current view → Advanced mode
Rule: Every style MUST use at least Level 1 + Level 3. Level 3 (rowFormatter) is what creates the "I can't believe it" impact. Column formatting alone is a 3/10.
The Style Application Workflow
Step 1: Read the list schema — required before generating any JSON
Know the columns, their internal names, types, and Choice values. Get this from SHAREPOINT.md if available, or ask the user. Do not generate any JSON until you have the actual column names and Choice values.
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.
- 9d ago First seen · 233 lines · 85 tokens per session scan B 9b755557922f
list-styling is a skill published in the GitHub repository pnp/sharepoint-skills (110 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 3,411 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ve-terminal-mono
OpenDesign from the CLI: driving the full design workflow with the od command — scripted, composable, agent-ready. Built as a decision-grade AI literacy deck for developers, power users.
frontend-slides
OpenDesign as a worked AI-workflow example: how local agents read your files and design on your desktop — concretely. Built as a decision-grade AI literacy deck for teams new to AI, leadership.
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.
html-ppt-obsidian-claude-gradient
OpenDesign's enterprise AI-adoption brief: local-first agents at work, the risk controls, the ROI, and the rollout plan. Built as a decision-grade AI literacy deck for leadership, IT, security.
octopus-ui-ux-design
Design UI/UX systems with style guides, palettes, typography, and component specs for new interfaces.
skill-design-lineage
Persist design documents with branch tracking, revision chains, and cross-session discovery.