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/wirasm/dylan/claude-mdgit clone --depth 1 https://github.com/Wirasm/dylanWhat 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 | $0.02386 | $0.02386 |
| Opus 5 | $0.01193 | $0.01193 |
| Sonnet 5 | $0.00477 | $0.00477 |
| Haiku 4.5 | $0.00239 | $0.00239 |
Grade A, and why
dylan CLAUDE.md scanned grade A with 1 finding 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 2d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
process = subprocess.run(command, check=True) How it starts
The opening of the file, as written. The whole thing — 330 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.
Core Principles
KISS (Keep It Simple, Stupid): Simplicity should be a key goal in design. Choose straightforward solutions over complex ones whenever possible. Simple solutions are easier to understand, maintain, and debug.
YAGNI (You Aren't Gonna Need It): Avoid building functionality on speculation. Implement features only when they are needed, not when you anticipate they might be useful in the future.
Dependency Inversion: High-level modules should not depend on low-level modules. Both should depend on abstractions. This principle enables flexibility and testability.
Open/Closed Principle: Software entities should be open for extension but closed for modification. Design your systems so that new functionality can be added with minimal changes to existing code.
KEEP early versions of new concepts in the concept_library/ directory very light and simple. we add complexity step by step and only if needed.
Minimal claude code wrappers with 0 to minimal validation.
- Always remember to use uv run when we run scripts
- We never write commit messages, we have a pre-commit hook for that so always commit with git commit nothing more
Example Claude Code Usage
# Simple prompt
claude -p "make a hello.js script that prints hello" --allowedTools "Write" "Edit"
# Using in a script
#!/usr/bin/env -S uv run --script
import subprocess
prompt = """
GIT checkout a NEW branch.
CREATE src/cc_todo/todo.py: a zero library CLI todo app with basic CRUD.
THEN GIT stage, commit and SWITCH back to main.
"""
command = ["claude", "-p", prompt, "--allowedTools", "Edit", "Bash", "Write"]
process = subprocess.run(command, check=True)
print(f"Claude process exited with output: {process.stdout}")
Claude Code Tools Reference
Claude Code has access to various tools. Here are the most commonly used ones:
| Tool | Description | Permission Required |
|---|---|---|
| Agent | Runs a sub-agent to handle complex, multi-step tasks | No |
| Bash | Executes shell commands in your environment | Yes |
| Glob | Finds files based on pattern matching | No |
| Grep | Searches for patterns in file contents | No |
| LS | Lists files and directories | No |
| Read | Reads the contents of files | No |
| Edit | Makes targeted edits to specific files | Yes |
| MultiEdit | Makes targeted edits to multiple files | Yes |
| Write | Creates or overwrites files | Yes |
| NotebookEdit | Modifies Jupyter notebook cells | Yes |
| NotebookRead | Reads and displays Jupyter notebook contents | No |
| WebFetch | Fetches content from a specified URL | Yes |
| WebSearch | Searches the web for information | Yes |
| TodoRead | Reads todo files | No |
| TodoWrite | Writes to todo files | Yes |
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.
- 2d ago First seen · 330 lines · 2,386 tokens per session scan A 448d9420933e
dylan CLAUDE.md is an instructions file published in the GitHub repository Wirasm/dylan (37 stars, last pushed 9mo ago), licensed MIT. It adds 2,386 tokens to every session, about $0.0119 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.