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 manishiitg/coding-agent-loop --skill tax-exportgit clone --depth 1 https://github.com/manishiitg/coding-agent-loopWrote 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/manishiitg/coding-agent-loop/tax-export)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/tax-export"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/tax-export/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/manishiitg/coding-agent-loop/tax-export"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/tax-export.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 | $0.00021 | $0.00791 |
| Opus 5.5 | $0.00008 | $0.00316 |
| Sonnet 5.5 | $0.00004 | $0.00158 |
| Haiku 4.5 | $0.00002 | $0.00079 |
Grade A, and why
tax-export 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 20d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tax Export Preparer
Use this skill when the owner wants to organize authorized records for a tax handoff. This skill can coexist with Finance Analyst in one Crew. Keep the Crew's identity and other template files intact.
Setup
Read templates/tax-export/TEMPLATE_SETUP.json and templates/tax-export/SETUP.md. Work through pending checks in chat. Add a check ID to completed_steps only after verifying its instructions. Preserve the checklist and earlier progress. An explicit decision to skip an optional connection or delivery route completes that optional check.
Export
- Confirm period, jurisdiction, currency, source files, and the recipient's required format. Ask for missing details before producing a final export.
- Build a transaction table with stable source references, dates, amounts, currency, category, and any tax fields present in the source. Keep original values and any transformations traceable.
- Check duplicates, missing records, refunds, reversals, mixed currencies, and category ambiguity. Reconcile totals to source summaries when possible.
- Produce an export plus a separate exceptions list and a short handoff note stating sources, filters, assumptions, and unresolved questions.
Do not invent tax codes, determine final tax liability, file a return, alter accounting records, or send data to a third party without owner authorization. Route uncertain classification to the owner or their tax professional.
Fictional export and reconciliation
Input: one legal entity, September 2026, USD. Authorized processor export contains customer payment P-101 of 100 for invoice I-101, refund R-101 of 20 linked to P-101, fee F-101 of 3, and payout PO-101 of 77. Bank statement shows deposit D-101 of 77 linked to PO-101. The owner and professional have not supplied tax-category rules. The format below is a review sample, not a tax filing.
source_id,date,source_type,linked_id,original_amount,currency,normalized_signed_amount,classification_status,tax_code,source_ref
P-101,2026-09-10,customer_payment,I-101,100.00,USD,100.00,pending_review,,processor:P-101
R-101,2026-09-12,customer_refund,P-101,20.00,USD,-20.00,pending_review,,processor:R-101
F-101,2026-09-12,processor_fee,P-101,3.00,USD,-3.00,pending_review,,processor:F-101
D-101,2026-09-15,bank_transfer,PO-101,77.00,USD,77.00,non_income_transfer,,bank:D-101
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 20d ago First seen · 38 lines · 21 tokens per session scan A 33389725b30a
tax-export is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 21 tokens to every session and 791 once invoked, about $0.0001 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
agency-legal-billing-time-tracking
Comprehensive legal billing and time tracking specialist for accurate time capture, invoice generation, billing narrative writing, collections management, trust account compliance, and billing analysis — maximizing revenue recovery while maintaining client relationships and ethical compliance across any firm size or…
agency-loan-officer-assistant
Comprehensive loan officer assistant for mortgage and lending professionals — covering borrower intake, pre-qualification, document collection, pipeline management, compliance tracking, rate quoting, and closing coordination across residential, commercial, and consumer lending.
gridcraft
Headless spreadsheets with GridCraft (XLSX/CSV/TSV workbooks, formula evaluation, recalculation, PDF export), provisioned on demand by pi-craft. Use for "build a budget spreadsheet with formulas", "convert this xlsx to csv", "what does this formula evaluate to", "change a cell and recalculate the totals", "export the…
regulatory-analysis
Analyzes documents and processes against FINRA, SEC, Federal Reserve, and CFPB regulatory frameworks. Identifies compliance gaps, classifies findings by severity, and recommends remediation. Use when performing compliance audits, regulatory reviews, gap analyses, or verifying policy adherence to financial regulations.
document-review
Reviews financial documents (prospectuses, ADVs, marketing materials) for FINRA 2210 compliance, required disclosures, and balanced presentation. Use when reviewing financial statements, audit documents, regulatory filings, or when the user mentions compliance checks, financial audits, or document verification.
goga-cell-go
Golang rules for implementing CODEMANIFEST contracts.