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 invoice-po-reconciliationgit 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/invoice-po-reconciliation)<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/invoice-po-reconciliation"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/invoice-po-reconciliation/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/invoice-po-reconciliation"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/invoice-po-reconciliation.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.01435 |
| Opus 5 | $0.00000 | $0.00718 |
| Sonnet 5 | $0.00000 | $0.00287 |
| Haiku 4.5 | $0.00000 | $0.00144 |
Grade A, and why
invoice-po-reconciliation 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invoice vs. Purchase Order Reconciliation
Purpose
Reconcile one or more user-selected invoice files against their corresponding purchase orders (POs). Determine compliance by comparing totals, write results back to invoice metadata, and return a clear summary.
Trigger Phrases
Activate this skill when the user says any of the following (or close variations):
- "po reconciliation"
- "invoice reconciliation"
- "reconcile invoice"
- "invoice to po reconciliation"
- "reconcile po"
- "match invoice to po"
- "invoice po match"
- "check invoice against po"
- "po match"
- "compare invoice to po"
Prerequisites
- The user must have one or more invoice files selected in a document library.
- If no files are selected, ask the user to select the invoice file(s) they want to reconcile.
Steps (repeat for each selected invoice)
Step 1 — Read Invoice Metadata
Use cat_file or list_items (with field projection) to read the selected invoice file's metadata columns. Look for:
- Invoice Number
- Invoice Total (or Amount, Total, Invoice Amount — adapt to actual column name)
- PO Number (or Purchase Order Number, Referenced PO — adapt to actual column name)
If the library has metadata columns populated, extract the values directly.
If metadata columns are missing or empty, read the file content with cat_file and extract Invoice Number, Invoice Total, and PO Number from the document body.
Step 2 — Find the Matching Purchase Order
Search the Purchase Order library (also try "Purchase Orders" or "PO" if not found) for a record whose PO Number column matches the PO Number extracted from the invoice.
- Primary method: Use
list_itemswith a filter on the PO Number column. - Fallback method: If the library doesn't have a clear PO Number column or the filter returns no results, use
find_itemsorsemantic_searchto locate the PO by PO number.
If no matching PO is found, report the invoice as Unable to Reconcile — No matching PO found and move to the next invoice.
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 · 107 lines · 0 tokens per session scan A 6ace37b405c3
invoice-po-reconciliation is a skill published in the GitHub repository pnp/sharepoint-skills (118 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,435 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
model-cost-compare
Starter: compare model costs for a described task — maps task shape to the cheapest adequate seat and shows the price spread.
ai-pricing
When the user wants to price an AI product, choose a charge metric, design pricing tiers, or optimize margins. Also use when the user mentions 'AI pricing,' 'usage-based pricing,' 'consumption pricing,' 'outcome pricing,' 'BYOK,' 'bring your own key,' 'per-seat pricing,' 'pricing tiers,' 'AI margins,' 'cost per…
stripe-refund-auditor
Audits Stripe refunds over a date range to surface anomalies (refund-rate spikes, missing reasons, duplicate refunds). Activates when the user asks to "audit refunds", "check Stripe refund anomalies", or "review refund activity".
carta-compensation-scorecard
Carta Total Compensation scorecard — shows how a corporation's employees compare to market. Two lenses: corporation-level rollup (band distribution — what % of employees are below / at / above market) and per-employee scorecard (each employee's compa-ratio + percentile + market band). Triggered by queries like…
carta-interaction-reference
Carta's behavioral rules for AI agents presenting cap table data — mandatory context for any Carta cap table response. Load ONCE per conversation, before the first such response (ownership, grants, SAFEs, valuations, waterfall scenarios, financing history, stakeholders, convertible instruments, option pools, or any…
carta-cap-table:issuance-review
Internal artifact sub-skill for carta-issuance. Renders a read-only HTML review summary for option-grant AND certificate issuance batches — stat tiles plus one confirmation row per stakeholder. Not invocable directly — dispatched by carta-issuance Phase 2 via artifact-manager:render-panel.