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 PostOakLabs/ainumbers --skill payments-day-end-to-endgit clone --depth 1 https://github.com/PostOakLabs/ainumbersWrote 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/postoaklabs/ainumbers/payments-day-end-to-end)<a href="https://agentmods.dev/skills/postoaklabs/ainumbers/payments-day-end-to-end"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/payments-day-end-to-end/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/postoaklabs/ainumbers/payments-day-end-to-end"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/payments-day-end-to-end.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 | $0.00066 | $0.00719 |
| Opus 5.5 | $0.00026 | $0.00288 |
| Sonnet 5.5 | $0.00013 | $0.00144 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
payments-day-end-to-end 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 15d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A payments day from start to finish
One payments day: validate the pain.001, parse the camt.053, reconcile, predict fails, price CSDR penalties, seal the evidence.
Prompt
Run one payments day end to end and leave evidence a regulator and an auditor can both check.
- Validate a synthetic pain.001 with pain001_validate; fix the reported defects in the input and re-run until clean. Record the hash.
- Parse a synthetic camt.053 with camt053_parse, then recon_match the statement lines against the pain.001 batch. Report matched / unmatched with reasons.
- Run verify_address_migration_batch on the beneficiary addresses to check ISO 20022 structured-address readiness.
- Predict fails with predict_settlement_fail on today's trades, price the CSDR penalties with calculate_csdr_penalty, and model buy-in exposure with model_buy_in_exposure. Then run run_t1_readiness_diagnostic and list the top three gaps.
- Call build_evidence_pack over every hash from steps 1-4 with the kernel_digests from chaingraph.json.
- On helmd: catalog.search "2052a", workflow.dry_run the daily classify pack, artifact.verify it, and note that the export needs a human consent ticket; do not request one.
- Anchor the evidence pack digest with anchor_stamp on OpenTimestamps. Give me the ledger link for the pack and a one-page day-end note: counts, exceptions, penalties, T+1 gaps, and how each number is re-verified without contacting us. Call shape: every ChainGraph node tool takes its arguments nested under one wrapper object, e.g. {"policy_parameters": { ... }}; flat arguments are discarded by schema validation. If a named tool is not in your tool list, call call_tool with { "name": "", "arguments": { … } }. It runs the same validation and returns the same receipt. GPU note: the verify_address_migration_batch tool computes in your browser, so the MCP endpoint returns no execution_hash; export the Policy Mandate artifact the page produces and pass that full artifact to verify_execution_hash as claimed_hash.
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.
- 15d ago Changed d3dfffcf8e1a
- 19d ago First seen · 42 lines · 66 tokens per session scan A 36d607367ffc
payments-day-end-to-end is a skill published in the GitHub repository PostOakLabs/ainumbers (11 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 719 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 2026-09-27.
Other skills, from other repositories
client-reporting-delivery
Design, generate, and deliver client performance reports across all channels, covering quarterly reports, tax reporting, portal integration, and compliance review. Use when the user asks about building or redesigning report templates, choosing what to include in quarterly or annual client reports, transitioning from…
risk-assessment
Deterministic heuristic risk scoring using a four-factor weighted model (Geographic 30%, Customer 35%, Product 25%, Channel 10%) aligned with Basel III, EBA Guidelines, FATF standards, and FinCEN guidance. Bands: LOW (0-20), MEDIUM (21-60), HIGH (61-80), CRITICAL (81-100).
transaction-monitoring
AML transaction monitoring for ongoing customer relationships. Identifies suspicious patterns including structuring, layering, and unusual activity. Assesses against regulatory thresholds and prepares Suspicious Activity Reports (SARs) with HITL decision gates.
csv-importer
A tool for importing transaction CSV files—spreadsheet files separated by commas—from Japanese accounting software and classifying every imported row.
tax-calculator
Calculate tax implications of trades and generate tax reports.
ppt-template-creator
Creates self-contained PPT template SKILLS (not presentations) from user-provided PowerPoint templates. Use ONLY when a user wants to create a reusable skill from their template. For creating actual presentations, use the pptx skill instead.