What is claudecode CLAUDE.md?

A set of working rules for an AI coding agent, covering planning, memory use, specifications, delegation, and verification. It describes how the agent should organise and check multi-step coding work.

Use it to guide coding-agent behaviour on projects that need structured planning, technical specifications, delegated subtasks, progress tracking, and verification.

It provides a consistent process for gathering context, planning changes, protecting the main conversation from unnecessary detail, and checking results before declaring work complete.

How ritheshh-cmyk/claudecode configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ritheshh-cmyk/claudecode. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ritheshh-cmyk/claudecode/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ritheshh-cmyk/claudecode

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ritheshh-cmyk/claudecode/claude-md/github.svg)](https://agentmods.dev/instructions/ritheshh-cmyk/claudecode/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ritheshh-cmyk/claudecode/claude-md"><img src="https://agentmods.dev/badge/instructions/ritheshh-cmyk/claudecode/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ritheshh-cmyk/claudecode/claude-md"><img src="https://agentmods.dev/badge/instructions/ritheshh-cmyk/claudecode/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,126 This file is loaded in full into every session.

When invoked 2,126 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02126	$0.02126
Opus 5	$0.01063	$0.01063
Sonnet 5	$0.00425	$0.00425
Haiku 4.5	$0.00213	$0.00213

Measured 9d ago against content hash 3f640a31c55f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claudecode 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 9d 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 · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Antigravity Global Rules & Protocols

This file defines the core behavioral rules and default protocols for the Antigravity agent. These rules must be checked and adhered to at the start of every session and during task execution.

1. Plan Mode is the Default

3+ Step Tasks: Any task that requires 3 or more steps must start in plan mode.
Context First: Before creating any plan or spec, always query the context first using memory_recall or memory_smart_search to retrieve relevant history, and verify codebase structure using the manifest.
Protocol: Every time you enter the planning phase, always use the gsd-plan-phase (or corresponding gsd-spec-phase / gsd-progress planning) skill to structure, specify, and review the plan before execution.
Spec Compliance: Map all technical specifications, data structures, and API contracts using openspec before changing any code.
Dynamic Re-planning: If execution goes sideways, stops, or encounters unexpected errors, halt immediately and re-plan.
Upfront Specs: Write detailed, technical specifications before changing any source code.

2. Subagents Protect the Main Context

Delegation: Offload extensive research, parallel analysis, and code exploration tasks to subagents.
Protocol: For complex research, query audits, or open-ended codebase exploration, use the deep-research skill pack (or search-specialist / tavily-web / search_web tools) to gather information thoroughly before designing a solution.
Focus: Equip each subagent with exactly one focused task to conserve the main context.
Compute Scalability: Allocate more compute resources/subagents to solve complex, concurrent sub-problems.

3. The Self-Improvement Loop

Persistent Lessons: Every correction, mistake, or session refinement must be documented as a rule in tasks/lessons.md.
Session Setup: Review tasks/lessons.md at the start of every session to inherit all historical learnings.
Efficiency: Compounded micro-rules keep context clean; 100 lines of precise lessons beat 800 lines of repetitive context.

Read the full file on GitHub · 85 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.

9d ago First seen · 85 lines · 2,126 tokens per session scan A 3f640a31c55f

Subscribe to this mod's changes

claudecode CLAUDE.md is an instructions file published in the GitHub repository ritheshh-cmyk/claudecode (24 stars, last pushed 8d ago), licensed MIT. It adds 2,126 tokens to every session, about $0.0106 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.

Building agents

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

claudecode: Instructions file for Claude Code