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 check-technologies/mcp-server-check --skill payroll-audit-reportgit clone --depth 1 https://github.com/check-technologies/mcp-server-checkWrote 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/check-technologies/mcp-server-check/payroll-audit-report)<a href="https://agentmods.dev/skills/check-technologies/mcp-server-check/payroll-audit-report"><img src="https://agentmods.dev/badge/skills/check-technologies/mcp-server-check/payroll-audit-report/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/check-technologies/mcp-server-check/payroll-audit-report"><img src="https://agentmods.dev/badge/skills/check-technologies/mcp-server-check/payroll-audit-report.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 3 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00080 | $0.01857 |
| Opus 5 | $0.00040 | $0.00928 |
| Sonnet 5 | $0.00016 | $0.00371 |
| Haiku 4.5 | $0.00008 | $0.00186 |
Grade A, and why
payroll-audit-report 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 10d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Payroll Audit Report
This skill generates a structured audit report for a company's payrolls over a specified date range. It pulls payroll data, aggregates totals per pay period, and flags anomalies that may warrant investigation.
Prerequisites
Collect two things from the user:
- A Check company ID (looks like
com_XXXXXXXXXXXXXXXXXX). Ask for it if not provided. - A date range — start and end dates for the audit window (e.g., "Q1 2025" or "2025-01-01 to 2025-03-31"). If no range is given, default to the last 3 months and confirm with the user.
Step 1: Gather Company Context
Pull the company details for context:
run_tool: get_company { "company_id": "<company_id>" }
Note the company name for the report header.
Step 2: Pull Payrolls in the Date Range
Fetch all payrolls whose payday falls within the audit window:
run_tool: list_payrolls {
"company": "<company_id>",
"payday_after": "YYYY-MM-DD",
"payday_before": "YYYY-MM-DD",
"limit": 100
}
Convert the user's date range to YYYY-MM-DD format:
payday_after— the start of the range (inclusive)payday_before— the end of the range (inclusive)
If there are more results than the limit, paginate using the cursor parameter until
all payrolls are fetched.
Tell the user how many payrolls were found before proceeding:
Found 6 payrolls for Acme Corp between 2025-01-01 and 2025-03-31.
Fetching details for each payroll...
If no payrolls are found, inform the user and stop.
Step 3: Fetch Payroll Details
For each payroll, use the composite tool to get items and contractor payments in one call:
run_tool: get_payroll_details {
"payroll_id": "<payroll_id>",
"include_items": true,
"include_contractor_payments": true,
"item_limit": 50
}
For payrolls with more than 50 items, note this limitation to the user. Most payrolls will be well under this limit.
Give progress updates for large sets (e.g., "Fetched 3/6 payrolls...").
Step 4: Pull Worker Headcounts for Cross-Reference
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.
- 10d ago First seen · 207 lines · 80 tokens per session scan A b9f14bb06283
payroll-audit-report is a skill published in the GitHub repository check-technologies/mcp-server-check (18 stars, last pushed 5d ago), licensed MIT. It adds 80 tokens to every session and 1,857 once invoked, about $0.0004 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
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.