What is claude-code-agents CLAUDE.md?

A set of development instructions for Claude Code, an AI coding assistant, that defines a required process for researching, planning, implementing, and checking changes.

Use it to organize coding tasks with a todo list, select applicable project rules, control the number of changed files, and verify the result before finishing.

It prevents implementation from starting before the task is broken down and the user has approved edits, while also requiring quality checks.

How rcdelacruz/claude-code-agents configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to rcdelacruz/claude-code-agents. 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/rcdelacruz/claude-code-agents/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/rcdelacruz/claude-code-agents

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/rcdelacruz/claude-code-agents/claude-md/github.svg)](https://agentmods.dev/instructions/rcdelacruz/claude-code-agents/claude-md)

Your own site

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

Per session 1,050 This file is loaded in full into every session.

When invoked 1,050 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	$0.01050	$0.01050
Opus 5.5	$0.00420	$0.00420
Sonnet 5.5	$0.00210	$0.00210
Haiku 4.5	$0.00105	$0.00105

Measured 2mo ago against content hash c127386db1e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-code-agents 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 2mo 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 · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Development Rules

Core rules for maximizing AI execution accuracy. All instructions must follow this file.

🚨 Most Important Principle: Research OK, Implementation STOP

User approval is mandatory before using any Edit/Write/MultiEdit tools

Reason: To prevent implementations that differ from user intent and ensure correct direction

Mandatory Execution Process

Execution Flow (Required Steps)

Task decomposition with TodoWrite → Cannot proceed to implementation without it Reason: To structure tasks and enable progress tracking
Execute rule-advisor → Understand task essence and select appropriate rules Reason: To select appropriate rules and understand task essence
Use Edit/Write/MultiEdit → User approval is mandatory Reason: Practicing the most important principle (Research OK, Implementation STOP)
Execute implementation → Cannot complete with quality check errors Reason: To ensure high-quality code
Count file changes → Auto-stop when threshold exceeded Reason: To get confirmation before impact becomes too large

TodoWrite and Metacognition Integration

Execution Rules:

When pending → in_progress: rule-advisor output is mandatory
After rule-advisor execution: Always update TodoWrite (revise task content, priority, granularity)
- Concretize task description based on taskEssence
- Reflect firstActionGuidance in the first task
- Restructure tasks considering warningPatterns
Using Edit tools without TodoWrite: Stop as rule violation
When updating task status: Recording implementation details is mandatory (no blanks)

Execution Prerequisites

rule-advisor output → JSON response must exist
TodoWrite task → in_progress status must exist
User approval record → Explicit approval before Edit/Write
Quality check results → Cannot complete with errors > 0

Prohibited Actions

Using any type → Causes type check errors Reason: Destroys type safety and causes runtime errors
Using Edit without TodoWrite → Rule violation Reason: Cannot track progress or ensure quality without task management
Edit/Write/MultiEdit without approval → Move to approval waiting Reason: To prevent violating the most important principle
Declaring completion with quality errors → Does not meet completion criteria Reason: To prevent incomplete code from being mixed in

Read the full file on GitHub · 110 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.

2mo ago First seen · 110 lines · 1,050 tokens per session scan A c127386db1e0

Subscribe to this mod's changes

claude-code-agents CLAUDE.md is an instructions file published in the GitHub repository rcdelacruz/claude-code-agents (2 stars, last pushed 1y ago), licensed MIT. It adds 1,050 tokens to every session, about $0.0042 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 2026-08-31.

claude-code-agents CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-code-agents CLAUDE.mdrcdelacruz/claude-code-agents	Instructions file	2	1y ago	MIT	A	1,050	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

claude-code-agents: Instructions file for Claude Code