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 perniemann/pnCore --skill pn-gl-reconcilergit clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/perniemann/pncore/pn-gl-reconciler)<a href="https://agentmods.dev/skills/perniemann/pncore/pn-gl-reconciler"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-gl-reconciler/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/perniemann/pncore/pn-gl-reconciler"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-gl-reconciler.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 | $0.00072 | $0.01347 |
| Opus 5.5 | $0.00029 | $0.00539 |
| Sonnet 5.5 | $0.00014 | $0.00269 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade A, and why
pn-gl-reconciler 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 1mo 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GL reconciler
When to use
- Month-end or period-end close: comparing GL trial balance to subledger, sub-system, or bank statement.
- Break investigation: a prior reconciliation flagged open items that need root-cause triage.
- Pre-audit preparation: clean up open items before external review.
- NAV tie-out support for fund admin workflows.
Pre-requisites
Load get_skill("pn-fsi-analyst-discipline"). Confirm what was supplied:
- GL trial balance (by account, period).
- Subledger or contra source (bank statement, sub-system export, custodian report).
- Prior reconciliation (if this is a continuation / aging review).
State the as-of date and account scope at the top of the output.
Instructions
1. Ingest and normalize
- Parse both sources to a common format: account code, description, debit/credit, period, amount.
- Normalize sign convention: establish which is the "book" side and which is the "source" side; state the convention.
- Flag any line where currency, date, or account mapping is ambiguous before proceeding.
2. Match
For each GL line, attempt to match to a source line using:
- Exact match: Same amount, same date, same reference number.
- Partial match: Same amount, different date (timing item) or different reference (possible re-booking).
- Aggregate match: Multiple source lines sum to one GL line or vice versa (split / aggregate posting).
Record match status for every line. Do not discard unmatched items.
3. Identify breaks
A break is any GL line with no matched source line (or vice versa). For each break:
| Field | Value |
|---|---|
| Account | |
| Description | |
| Amount | |
| Age (days since first appearance) | |
| Book side / Source side | |
| Prior period carry-forward? |
4. Root cause triage
Categorize each break into one of:
| Category | Description |
|---|---|
| Timing | Transaction in GL but not yet in source (or vice versa); expected to clear within N days |
| Booking error | Wrong account, wrong amount, or duplicate posting on one side |
| Missing entry | Transaction in source with no corresponding GL entry |
| Reclassification needed | Posted to wrong cost center, entity, or account; correct posting exists elsewhere |
| Disputed / investigation | Amount or transaction cannot be explained by available data; requires external input |
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.
- 1mo ago First seen · 130 lines · 72 tokens per session scan A b04678f53167
pn-gl-reconciler is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 1,347 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
typescript
TypeScript coding conventions, best practices, and patterns for writing clean, maintainable code.
metronome
Guides Metronome usage-based billing integration decisions — event ingestion (single and batch, idempotency, billable metrics), contract design (rate cards, overrides, dimensional pricing, products), invoicing lifecycle (grace periods, finalization, Stripe sync), credit and commit management (prepaid, postpaid…
stripe-best-practices
Guides Stripe integration decisions across development and test environment planning (separate sandboxes vs the shared test mode sandbox), API selection (Checkout Sessions vs PaymentIntents), Connect platform setup (Accounts v2, controller properties), billing/subscriptions, tax and registrations (Stripe Tax…
comparable-company-analysis
A workflow for comparing a publicly listed company with similar listed companies. It examines their businesses, financial results, competitors, and recent developments.
财经分析工具包
A set of finance analysis tools for stocks, markets, portfolios, and financial news. It includes data retrieval, technical indicators such as moving averages and RSI, trend analysis, risk assessment, and allocation suggestions.
business-case
Business case analysis with ROI, NPV, IRR, payback period, and TCO calculations for investment decisions. Use when building financial justification, cost-benefit analysis, build-vs-buy comparisons, or sensitivity analysis.