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 agentmods add instructions/shivprime94/file-itr/agents-mdgit 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/instructions/shivprime94/file-itr/agents-md)<a href="https://agentmods.dev/instructions/shivprime94/file-itr/agents-md"><img src="https://agentmods.dev/badge/instructions/shivprime94/file-itr/agents-md.svg" alt="Measured on agentmods" 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 | $0.00534 | $0.00534 |
| Opus 5 | $0.00267 | $0.00267 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
file-itr AGENTS.md 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 5d 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
Agent instructions for file-itr
For AI coding agents working in this repository. Claude Code loads this file
automatically via the @AGENTS.md import in CLAUDE.md; any other
agent that reads AGENTS.md directly gets the same content — there is one
copy, not two.
What this repo is
Two independent things live here — see README.md for the full layout:
- The skill (
skills/itr-india/SKILL.md+references/) — an agent skill that files Indian income tax returns. This is what actually runs when a user invokes the skill. - The engine (
skills/itr-india/engine/) — a separate, tested Python tax engine that independently verifies the skill's numbers. It is not loaded bySKILL.mdand not part of the.skillbundle — see engine/README.md.
Before you touch anything
- Every statutory number or rule needs a verified citation. No rule goes
in on "this sounds right" — see
engine/README.md for the
Rule/ citation/fail-loud discipline this repo holds itself to, and apply the same standard toreferences/*.md. - Never commit real tax data (PAN/Aadhaar, account numbers, credentials, Form 16/26AS/AIS/ITR JSON — real or unredacted, in a commit, test fixture, or PR description). See SECURITY.md.
- Never hand-edit or hand-commit
itr-india.skill. CI rebuilds it deterministically fromSKILL.md/references//evals/on every push that touches those paths — see.github/workflows/skill-bundle.yml. - Run the engine's tests before and after any engine change:
pytest skills/itr-india/engine/tests -v. CI runs this on every push/PR (.github/workflows/engine-tests.yml); keep it green.
Full guidelines
CONTRIBUTING.md has dev setup, the commit-message convention this repo uses, and PR expectations — read it before making a change, not just this file.
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.
- 5d ago First seen · 43 lines · 534 tokens per session scan A 90cbad30f9ec
file-itr AGENTS.md is an instructions file published in the GitHub repository shivprime94/file-itr (526 stars, last pushed 26d ago), licensed MIT. It adds 534 tokens to every session, about $0.0027 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 instructions, from other repositories
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
LLM-TradeBot copilot-instructions.md
Copilot instructions for EthanAlgoX/LLM-TradeBot, covering repository instructions, core rules, validation and ai asset governance.
Convertible-Bond-Pricing-Research CLAUDE.md
Instructions for ericxuzhesheng/Convertible-Bond-Pricing-Research, covering claude.md — convertible bond pricing research, current published state and routine commands.
bukio-cli AGENTS.md
AGENTS.md instructions for erikvankempen/bukio-cli, covering agents.md — bukio-cli agent manual, 1. house rules (non-negotiable), 2. environment, 3. command quick reference and 3.1 jurisdiction profiles (16 markets).
swiss-snb-mcp CLAUDE.md
Claude Code instructions for malkreide/swiss-snb-mcp, covering claude.md, teil 1 — konventionen (portfolio-weit), vor der arbeit, tests and wenn etwas rot ist.