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 shivprime94/file-itr --skill itr-indiagit clone --depth 1 https://github.com/shivprime94/file-itrWrote 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/shivprime94/file-itr/itr-india)<a href="https://agentmods.dev/skills/shivprime94/file-itr/itr-india"><img src="https://agentmods.dev/badge/skills/shivprime94/file-itr/itr-india/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/shivprime94/file-itr/itr-india"><img src="https://agentmods.dev/badge/skills/shivprime94/file-itr/itr-india.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00276 | $0.06065 |
| Opus 5 | $0.00138 | $0.03033 |
| Sonnet 5 | $0.00055 | $0.01213 |
| Haiku 4.5 | $0.00028 | $0.00607 |
Grade A, and why
itr-india 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 — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Filing an Indian Income Tax Return (ITR)
What this skill does and its boundaries
This skill turns Claude into a careful, methodical preparer for a resident Indian individual's income tax return — salaried, freelancer/creator, small business, investor, pensioner — under either the old or the new regime (non-resident / RNOR returns, with their DTAA / Form 67 / Schedule FSI-TR machinery, are out of scope — see step 1). The goal is a return where every rupee of income is reconciled to a source document, the cheaper regime is chosen by actual computation (not guesswork), the tax math is independently verified, and the user is walked cleanly through the portal up to (but not including) the actions only they may legally perform.
Read this whole file first, then pull in the reference files under references/
as each phase demands. The references hold the detail; this file holds the
workflow and judgment.
Hard boundaries — Claude must NOT do these; direct the user to do them:
- Enter or handle the user's portal password, bank credentials, card numbers, OTPs, or any secret. Logging in is the user's job.
- Make the tax payment (e-Pay Tax / net-banking / UPI / card). State the exact amount and head; the user pays.
- Click the final Submit / Proceed to e-Verify, or enter the Aadhaar OTP / EVC. Submission and verification are the user's legal acts.
- Give a confident "you should buy this policy / invest in X to save tax" recommendation. Claude is not a chartered accountant or financial adviser — lay out the factual options and trade-offs and let the user decide. Say this plainly when it matters.
Always tell the user up front: rules change every assessment year, AIS/26AS can be incomplete or wrong, and they remain responsible for the figures. This skill makes the return accurate and defensible, and picks the regime that is cheaper for them on their actual numbers — it does not minimise tax by claiming things that aren't real.
What ships with it
41 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.
- conftest.py 110 B runs code
- engine/__init__.py 0 B runs code
- engine/buckets.py 3.8 KB runs code
- engine/compute.py 5.6 KB runs code
- engine/form16.py 22 KB runs code
- engine/interest.py 9.3 KB runs code
- engine/model.py 4.0 KB runs code
- engine/rates.py 9.8 KB runs code
- engine/README.md 3.5 KB
- engine/rulebase.py 2.0 KB runs code
- engine/rules/__init__.py 0 B runs code
- engine/rules/ay2026_27.py 33 KB runs code
- engine/scope.py 2.4 KB runs code
- engine/setoff.py 7.2 KB runs code
- engine/tests/__init__.py 0 B runs code
- engine/tests/test_buckets.py 8.8 KB runs code
- engine/tests/test_compute.py 6.1 KB runs code
- engine/tests/test_employment.py 12 KB runs code
- engine/tests/test_form16.py 2.8 KB runs code
- engine/tests/test_interest.py 13 KB runs code
- engine/tests/test_model.py 2.2 KB runs code
- engine/tests/test_rates.py 14 KB runs code
- engine/tests/test_rulebase.py 1.7 KB runs code
- engine/tests/test_rules_ay2026_27.py 1.0 KB runs code
- engine/tests/test_scope.py 1.7 KB runs code
- engine/tests/test_setoff.py 9.3 KB runs code
- engine/tests/test_trace.py 2.2 KB runs code
- engine/trace.py 1.4 KB runs code
- evals/evals.json 7.5 KB
- references/capital-gains-other-sources.md 14 KB
- references/creator-44ada.md 5.6 KB
- references/deadlines-and-late-filing.md 6.1 KB
- references/deductions-old-regime.md 3.3 KB
- references/form-selection-ay2026-27.md 4.4 KB
- references/huf-filing.md 5.0 KB
- references/income-reconciliation.md 8.2 KB
- references/multiple-form-16.md 8.0 KB
- references/portal-workflow.md 7.9 KB
- references/tax-regimes-and-slabs.md 5.9 KB
- references/truthful-filing-safeguards.md 8.0 KB
- references/virtual-digital-assets.md 3.3 KB
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 · 418 lines · 276 tokens per session scan A 79b447a6f609
itr-india is a skill published in the GitHub repository shivprime94/file-itr (528 stars, last pushed 1mo ago), licensed MIT. It adds 276 tokens to every session and 6,065 once invoked, about $0.0014 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
expense-review-policy
Review invoices and contracts against accounts-payable policy before human approval.
kyc-doc-parse
Parse an investor or client onboarding packet into structured KYC fields — identity, ownership, control, source of funds, and document inventory. Use as the first step of KYC screening; output feeds the rules engine.
audit-support
Support SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits.
fiscaliste
Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…
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.
subcontractor-payment-tracker
Track subcontractor payments, lien waivers, and compliance. Manage payment schedules and documentation.