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 Wadhawnaiya/TallyMind --skill tally-doc-importgit clone --depth 1 https://github.com/Wadhawnaiya/TallyMindWrote 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/wadhawnaiya/tallymind/tally-doc-import)<a href="https://agentmods.dev/skills/wadhawnaiya/tallymind/tally-doc-import"><img src="https://agentmods.dev/badge/skills/wadhawnaiya/tallymind/tally-doc-import/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/wadhawnaiya/tallymind/tally-doc-import"><img src="https://agentmods.dev/badge/skills/wadhawnaiya/tallymind/tally-doc-import.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 | $0.00090 | $0.01750 |
| Opus 5 | $0.00045 | $0.00875 |
| Sonnet 5 | $0.00018 | $0.00350 |
| Haiku 4.5 | $0.00009 | $0.00175 |
Grade A, and why
tally-doc-import 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.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tally Document Import
Turn a folder of a client's real paperwork into Tally vouchers. This skill only
drafts and orchestrates — it never talks to Tally directly. All reading,
ledger lookups, and posting go through the tallymind MCP server's tools
(the same server the tally-mind skill uses), so every write still passes
through the existing preview → confirm gate.
Prerequisites
Confirm before starting:
- TallyPrime is running on the machine
tallymindis configured to reach, with the client's company loaded. - A folder path containing that client's documents for the period.
Call tally_doctor first. If a company other than the one currently active
is needed, call set_company(name) before doing anything else — every
lookup and write below applies to whichever company is active.
Workflow
1. Locate and read the documents
List the folder's contents and group files by extension: PDF, JPG/PNG (scans/photos), XLSX/XLS/CSV, and anything else.
- Read PDFs and images directly — Claude reads these natively, no OCR step needed.
- Read CSV files directly, they're already plain text.
- For XLSX files, run
python scripts/xlsx_to_csv.py <file>to get a plain-text table (the script is dependency-free stdlib, see the script's own header for its.xlslegacy-format limitation). The script has no access to cell number-formatting, so any date or percentage column prints as a raw underlying number (e.g. a date as45852, not2025-07-14) — treat any suspicious integer-looking column next to words like "date" as a formatted value and cross-check it against the source document rather than taking it at face value. - If a file can't be read or classified, don't skip it silently — carry it into the final batch summary as "unprocessed" with the reason.
2. Classify each document and extract the transaction
For each document, decide what kind of source it is and which Tally voucher
type it maps to (sales invoice, purchase bill, bank payment/receipt line,
expense receipt, credit/debit note, journal adjustment). The full mapping
table with worked examples is in references/voucher-mapping.md — consult
it before drafting entries for a document type not already handled in this
session.
What ships with it
3 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.
- 12d ago First seen · 155 lines · 90 tokens per session scan A 55f41859bd70
tally-doc-import is a skill published in the GitHub repository Wadhawnaiya/TallyMind (4 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 1,750 once invoked, about $0.0005 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 2026-08-31.
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.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.