Borrowing it
Nothing to install: this file belongs to sophonfinance-wq/finance-automation-portfolio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sophonfinance-wq/finance-automation-portfolio/main/.claude/skills/close/SKILL.mdgit clone --depth 1 https://github.com/sophonfinance-wq/finance-automation-portfolioWrote 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/sophonfinance-wq/finance-automation-portfolio/close)<a href="https://agentmods.dev/skills/sophonfinance-wq/finance-automation-portfolio/close"><img src="https://agentmods.dev/badge/skills/sophonfinance-wq/finance-automation-portfolio/close/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/sophonfinance-wq/finance-automation-portfolio/close"><img src="https://agentmods.dev/badge/skills/sophonfinance-wq/finance-automation-portfolio/close.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 | $0.00052 | $0.00407 |
| Opus 5 | $0.00026 | $0.00204 |
| Sonnet 5 | $0.00010 | $0.00081 |
| Haiku 4.5 | $0.00005 | $0.00041 |
Grade A, and why
close 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.
What it actually says
Month-End Close Engine
Package close_engine in monthly-close-automation/. All data fictional, seeded (default seed 2026). Integer-cent math.
Commands (run from monthly-close-automation/)
python -m close_engine --period 2026-03 --out ./output # full close; exit != 0 if not clean
python -m close_engine --demo-guardrails # inject 12 faults, prove all 10 controls (C1-C10) catch them
python -m close_engine.loop --demo --out output # AUTONOMOUS LOOP: resync drift from sub-ledger, quarantine C10 tamper
python -m pytest -q # 15,687 tests
Loop verdicts (close_engine/loop.py)
AUTO-POSTED (0) / AUTO-POSTED (PARTIAL) (0, something quarantined) / HALTED (1).
Boundary of autonomy: C10 locked-period tamper -> QUARANTINE (held, never overwritten); C1 broken opening TB -> HALT (never fabricated).
Key files
close_engine/engine.py— 7 recurring-entry classes, refuses out-of-tie postsclose_engine/sentinel/— controls C1-C10, shadow recompute, findingsclose_engine/faults.py— 12 seeded fault injectors (the drift vocabulary)close_engine/loop.py+loop_report.py— autonomous loop + Markdown/HTML reports
Windows consoles: set PYTHONIOENCODING=utf-8 if emoji banners crash.
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 · 28 lines · 52 tokens per session scan A 52b4917d4c1f
close is a skill published in the GitHub repository sophonfinance-wq/finance-automation-portfolio (11 stars, last pushed 15d ago), licensed MIT. It adds 52 tokens to every session and 407 once invoked, about $0.0003 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
Invoice Automation
Automate invoice generation, sending, tracking, and payment reconciliation across accounting platforms.
correction-memory
A local memory system that stores tax-accountant corrections to transaction classifications. It matches future transactions to earlier vendor or description patterns.
nightly-batch
Batch-process all client companies overnight. Fetches unprocessed transactions from freee API, runs the full classification pipeline, and generates a summary for morning review.
tax-classifier
A system for assigning Japanese business transactions to accounting categories, called 勘定科目, and consumption-tax treatments. It checks exclusions, past corrections, keywords, and then uses AI when needed.
csv-importer
A tool for importing transaction CSV files—spreadsheet files separated by commas—from Japanese accounting software and classifying every imported row.
bank-reconciliation
Match book entries against bank or credit card statements to find discrepancies, missing transactions, and duplicates. Uses exact, near, and batch matching with balance verification. Trigger on "reconcile bank statement", "match transactions", "bank balance doesn't match", "close the books".