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.
npx agentmods add instructions/krzemienski/claude-code-builder/claude-mdgit clone --depth 1 https://github.com/krzemienski/claude-code-builderWrote 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/krzemienski/claude-code-builder/claude-md)<a href="https://agentmods.dev/instructions/krzemienski/claude-code-builder/claude-md"><img src="https://agentmods.dev/badge/instructions/krzemienski/claude-code-builder/claude-md.svg" alt="Measured on agentmods" 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 | $0.01452 | $0.01452 |
| Opus 5 | $0.00726 | $0.00726 |
| Sonnet 5 | $0.00290 | $0.00290 |
| Haiku 4.5 | $0.00145 | $0.00145 |
Grade A, and why
claude-code-builder 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 4d 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 — 213 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.
Project Overview
Claude Code Builder (CCB) is an AI-powered Python CLI tool that automates the complete software development lifecycle. It transforms project specifications into production-ready applications through intelligent task decomposition, custom AI instruction generation, and systematic phase-based execution.
🚨 CRITICAL: MCP Server Usage is MANDATORY
Every operation MUST use the appropriate MCP server:
- context7: Before implementing ANY library or framework
- memory: After completing each task/module
- sequential-thinking: For complex problem decomposition
- filesystem: For ALL file operations (NEVER use Python's open())
- git: For version control after each phase
Key Development Commands
# Install dependencies
poetry install
# Run the CLI
poetry run claude-code-builder --help
poetry run claude-code-builder init spec.md --output-dir ./project
poetry run claude-code-builder resume ./project
poetry run claude-code-builder status ./project
poetry run claude-code-builder logs ./project --tail
# Development tools
poetry run ruff check .
poetry run ruff format .
poetry run mypy src/claude_code_builder/
poetry run black .
# Build and test
poetry build
pip install dist/*.whl
claude-code-builder --version
# Functional testing (NO UNIT TESTS)
python validate_build.py ./test_output
Architecture Overview
Multi-Agent System
src/claude_code_builder/
├── agents/
│ ├── spec_analyzer.py # Analyzes specifications
│ ├── task_generator.py # Creates task breakdowns
│ ├── instruction_builder.py # Generates AI instructions
│ ├── acceptance_generator.py # Creates test criteria
│ ├── documentation_agent.py # Generates docs
│ └── executor.py # Claude Code SDK execution
├── core/
│ ├── models.py # Pydantic v2 models
│ ├── logging_system.py # Multi-stream logging
│ ├── context_manager.py # 150K+ token handling
│ ├── mcp_orchestrator.py # MCP enforcement
│ ├── output_manager.py # Project directories
│ └── project_manager.py # State management
├── builders/
│ ├── claude_md_builder.py
│ ├── command_builder.py
│ └── documentation_builder.py
├── testing/
│ ├── acceptance_runner.py # Real-world tests only
│ └── production_validator.py
└── cli/
└── main.py # Click CLI entry
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.
- 4d ago First seen · 213 lines · 1,452 tokens per session scan A ea3643b0cd94
claude-code-builder CLAUDE.md is an instructions file published in the GitHub repository krzemienski/claude-code-builder (24 stars, last pushed 9mo ago), licensed MIT. It adds 1,452 tokens to every session, about $0.0073 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.
Other instructions, from other repositories
shep AGENTS.md
AGENTS.md instructions for shep-ai/shep, covering agents.md, project, spec workflow, commands and architecture.
shep CLAUDE.md
Claude Code instructions for shep-ai/shep, covering claude.md, project, spec workflow, commands and architecture.
grace-marketplace CLAUDE.md
Claude Code instructions for osovv/grace-marketplace, covering repository context, what this repo contains, core purpose, important working rules and how to think about changes.
ai-sdk-provider-claude-code AGENTS.md
AGENTS.md instructions for ben-vargas/ai-sdk-provider-claude-code, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
kodit CLAUDE.md
Instructions for helixml/kodit, covering helix development rules, setup, build, test, and check, shipping code and go.
ARBuilder CLAUDE.md
Instructions for Quantum3-Labs/ARBuilder, covering claude.md, project overview, repository structure, development commands and environment setup.