Borrowing it
Nothing to install: this file belongs to gargraman/claude-itr2-filing-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gargraman/claude-itr2-filing-skill/main/CLAUDE.mdgit clone --depth 1 https://github.com/gargraman/claude-itr2-filing-skillWrote 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/gargraman/claude-itr2-filing-skill/claude-md)<a href="https://agentmods.dev/instructions/gargraman/claude-itr2-filing-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/gargraman/claude-itr2-filing-skill/claude-md/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/instructions/gargraman/claude-itr2-filing-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/gargraman/claude-itr2-filing-skill/claude-md.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 | $0.01361 | $0.01361 |
| Opus 5.5 | $0.00544 | $0.00544 |
| Sonnet 5.5 | $0.00272 | $0.00272 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
claude-itr2-filing-skill CLAUDE.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 14d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this repo is
This is not an application — it is a Claude Agent Skill: a package of prose instructions (SKILL.md + references/*.md) that guides a resident Indian individual through filing ITR-2 / ITR-3 for AY 2026-27 (FY 2025-26). There is no code, no build system, no dependencies, no tests. "Editing this repo" means editing tax-domain markdown, and the correctness bar is factual/legal accuracy against Indian tax law — not a passing test suite.
There are no build, lint, or test commands. Validation is manual: re-read the changed reference against its cited source (incometax.gov.in circular, Finance Act 2025, ICAI Guidance Note), and check cross-references between files still line up (see "Invariants" below).
Architecture
The whole skill runs on progressive disclosure, and that constraint drives every structural decision:
SKILL.mdis the only file loaded up-front. It holds the YAML frontmatter (name,description— thedescriptionis what triggers the skill, so it enumerates every keyword a user might type), the hard gates, the load-on-demand table, and the 7-step workflow. It must stay small; it delegates all tax detail toreferences/.references/*.mdare loaded only when their topic becomes active during the workflow. SKILL.md's load-on-demand table (the "When to load" column) is the contract: each reference is pulled in at a specific step or on a specific trigger, never preloaded. When adding or renaming a reference, update that table in the same change.
The 7 steps are sequential and gated — Intake+form-selection → Schedule triage → Per-schedule walkthrough → AIS/26AS reconciliation → Regime comparison → Final summary (the CONFIRMED gate) → JSON generation. Output at every step is governed by references/output-format.md, which defines numbered templates (Template 0–7); the workflow steps reference those templates by number rather than improvising layout.
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.
- 14d ago First seen · 51 lines · 1,361 tokens per session scan A 51b2a90e811a
claude-itr2-filing-skill CLAUDE.md is an instructions file published in the GitHub repository gargraman/claude-itr2-filing-skill (3 stars, last pushed 14d ago), licensed MIT. It adds 1,361 tokens to every session, about $0.0054 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 2026-10-12.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.