file-itr AGENTS.md

file-itr AGENTS.md is an instructions file for Codex, OpenCode from shivprime94/file-itr. It costs 534 tokens per session, scanned A, original, MIT.

Repository guidance for AI coding agents working on a project that prepares Indian income tax returns and contains a separate Python tax-calculation engine.

In plain words
What is it for?
Use it when modifying this repository, especially its tax-return skill, tax engine, references, tests, or documentation.
Why use it?
It explains the project structure and safety rules before changes are made, including the need to cite tax rules and avoid committing real personal tax data.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/shivprime94/file-itr/agents-md
Clone the repo
git clone --depth 1 https://github.com/shivprime94/file-itr

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for file-itr AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shivprime94/file-itr/agents-md.svg)](https://agentmods.dev/instructions/shivprime94/file-itr/agents-md)
Your own site
<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>
Per session 534 This file is loaded in full into every session.
When invoked 534 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 5d ago against content hash 90cbad30f9ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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.

AGENTS.md · 43 lines

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 by SKILL.md and not part of the .skill bundle — 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 to references/*.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 from SKILL.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.

Changes

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.

  1. 5d ago First seen · 43 lines · 534 tokens per session scan A 90cbad30f9ec

Subscribe to this mod's changes

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.

Related

Other instructions, from other repositories