claude-setup CLAUDE.md

claude-setup CLAUDE.md is an instructions file for coding agents from RohitBind123/claude-setup. It costs 2,322 tokens per session, scanned A, original, MIT.

A set of working instructions for Claude Code, an AI coding assistant. It defines a development process that includes research, planning, test-driven development (writing tests before code), performance checks, reviews, and migration safety.

In plain words
What is it for?
Use it to guide feature development from research and planning through tests, implementation, code review, content review, and build verification. It also sets rules for asynchronous operations and database changes.
Why use it?
It gives the coding assistant a consistent process for building and reviewing software. The rules address common problems such as slow database access, unsafe data migrations, missing values, and unclear user-facing labels.

Instructions file

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/rohitbind123/claude-setup/claude-md
Clone the repo
git clone --depth 1 https://github.com/RohitBind123/claude-setup

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 claude-setup CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rohitbind123/claude-setup/claude-md.svg)](https://agentmods.dev/instructions/rohitbind123/claude-setup/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rohitbind123/claude-setup/claude-md"><img src="https://agentmods.dev/badge/instructions/rohitbind123/claude-setup/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,322 This file is loaded in full into every session.
When invoked 2,322 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 $0.02322 $0.02322
Opus 5 $0.01161 $0.01161
Sonnet 5 $0.00464 $0.00464
Haiku 4.5 $0.00232 $0.00232

Measured 3d ago against content hash e372919ac601, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-setup 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 3d 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.

CLAUDE.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Global Claude Code Instructions

You have the Everything Claude Code (ECC) system installed globally. Use it.

Workflow: Always Follow This Order

  1. Research First — Search for existing solutions, patterns, and implementations before writing code
  2. Plan First — Use /plan or the planner agent for any non-trivial feature
  3. TDD — Use /tdd or tdd-guide agent. Write tests first, then implement
  4. Perf by Default — Apply production-performance rules as you code (see Rules section). Never write sequential independent queries, N+1 patterns, or uncached stable data
  5. Data Quality by Default — Missing values are never rendered as 0. Internal enum keys never reach users. See rules/common/data-quality.md
  6. Async State Safety by Default — Mutations fire BEFORE UI transitions. Long-running flows support resume. See rules/common/async-state-safety.md
  7. Migration Safety by Default — Pre-migration audit, dedup before unique index, backfill scripts for new denormalized columns. See rules/common/migration-safety.md
  8. Code Review — Use /code-review or code-reviewer agent after writing code
  9. Content Quality Review — Use content-quality-reviewer agent before any user-facing launch
  10. Verify — Use /verify before committing

Production from Day 1

The five rule files below are non-negotiable for any new project. Apply them from the first commit, not as a post-launch cleanup. Each file was extracted from real session learnings where the reverse order cost days of rework.

Rule File What it prevents
rules/common/production-performance.md Sequential queries, N+1, missing cache, unsized pools
rules/common/data-quality.md Misleading zeros, internal fields in UI, silent fallthrough
rules/common/async-state-safety.md Race conditions, lost state on navigation, polling over SSE
rules/common/migration-safety.md Failed migrations, duplicate rows, blocking ALTER TABLEs
rules/typescript/production-performance.md No-persistence React Query, broad invalidations, inline JSX functions

Read the full file on GitHub · 196 lines

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. 3d ago First seen · 196 lines · 2,322 tokens per session scan A e372919ac601

Subscribe to this mod's changes

claude-setup CLAUDE.md is an instructions file published in the GitHub repository RohitBind123/claude-setup (2 stars, last pushed 4mo ago), licensed MIT. It adds 2,322 tokens to every session, about $0.0116 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.

Related

Other instructions, from other repositories

wallfacer CLAUDE.md

Instructions for changkun/wallfacer: If you didn't add a test, you didn't fix a bug. Every bug fix must include a reproducible test that fails without the fix and passes with it. You commit frequently, one small scope diff at a time. Push to main once a full batch of work is complete and verified. Leftover must be…

changkun/wallfacer · 133 tokens

arc AGENTS.md

AGENTS.md instructions for howells/arc, covering arc, shape, gotchas, editing constraints and search order.

howells/arc · 1,113 tokens

spec-driven-tdd AGENTS.md

Instructions for strelov1/spec-driven-tdd: This repo is a skill-pack. When implementing an OpenSpec change, invoke the spec-driven-tdd skill and follow its lifecycle: plan in OpenSpec, isolate in a worktree, implement each task via TDD → simplify → review, then finish + archive.

strelov1/spec-driven-tdd · 121 tokens

mcp-repo-onboarding AGENTS.md

Instructions for rogermt/mcp-repo-onboarding, covering agents.md — agent & copilot instructions, current status, output verification, project identity and ⚠️ critical: tdd required.

rogermt/mcp-repo-onboarding · 2,056 tokens

arxiv-agent-mcp AGENTS.md

AGENTS.md instructions for tbaraniuk/arxiv-agent-mcp, covering agents.md, roles, test-writer, implementer and per-task loop.

tbaraniuk/arxiv-agent-mcp · 451 tokens

think CLAUDE.md

Instructions for matiasvillaverde/think, covering claude.md, quick reference, hierarchical documentation, development philosophy and test-driven development (tdd).

matiasvillaverde/think · 1,689 tokens