ai-dev-playbook: Instructions file for Claude Code

CLAUDE.md

ai-dev-playbook CLAUDE.md is an instructions file for Claude Code from Geeksfino/ai-dev-playbook. It costs 1,159 tokens per session, scanned A, original, MIT.

A set of coding instructions for making small, deliberate changes in a codebase. It asks the developer to read related files and tests, state assumptions, consider tradeoffs, and keep solutions simple.

In plain words
What is it for?
Use it before changing code, especially when the project has established conventions or the requested behavior is unclear.
Why use it?
It reduces mistakes caused by guessing, skipping existing patterns, or writing more code than the task needs.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is Geeksfino/ai-dev-playbook's own configuration. It tells Claude Code how to work on ai-dev-playbook itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-dev-playbook configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Geeksfino/ai-dev-playbook. 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/Geeksfino/ai-dev-playbook/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Geeksfino/ai-dev-playbook

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.

agentmods badge for ai-dev-playbook CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/geeksfino/ai-dev-playbook/claude-md.svg)](https://agentmods.dev/instructions/geeksfino/ai-dev-playbook/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/geeksfino/ai-dev-playbook/claude-md"><img src="https://agentmods.dev/badge/instructions/geeksfino/ai-dev-playbook/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,159 This file is loaded in full into every session.
When invoked 1,159 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01159 $0.01159
Opus 5 $0.00580 $0.00580
Sonnet 5 $0.00232 $0.00232
Haiku 4.5 $0.00116 $0.00116

Measured 7d ago against content hash 9ec0b5edc919, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ai-dev-playbook 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 7d 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 · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

LLMs make the same mistakes repeatedly. These rules exist to prevent them.

1. Read Before You Write

Before writing anything:

  • Read the files you're about to modify. Not skim. Read.
  • Find how similar things are done elsewhere and follow that pattern.
  • Check existing imports — don't introduce a library the project doesn't use.
  • Look at test files to understand expected behavior, not assumed behavior.

If you don't see a pattern for something, ask: "I don't see a pattern for X — should I follow Y or do something different?"

2. Think Before You Code

State your assumptions. If the task is ambiguous, say what you're assuming before you start. "I'm assuming JWT auth with httpOnly cookies — let me know if you want something different." Guessing silently wastes hours.

Name the tradeoffs. "This trades memory for speed and introduces cache invalidation." Say it before writing 200 lines.

Present options briefly when they exist. Two, maybe three. With a recommendation. Not five.

If something is confusing, stop. Say what's confusing and ask. Don't fill confusion with plausible-sounding code.

3. Simplicity

Write the minimum code that solves this specific problem right now.

  • No premature abstraction. One email type needed? Write send_welcome_email(user), not an EmailService with a strategy pattern.
  • No speculative error handling. Only handle errors that can actually occur.
  • No unnecessary configurability. Hardcode things until there's a real reason not to.
  • No dead flexibility. Interfaces with one implementation, abstract classes with one child — these cost cognitive overhead and provide nothing until a second case exists.

Test: if someone asks "why is this abstracted?" and the answer is "in case we need to…" — revert it.

4. Surgical Changes

Your diff should be as small as possible.

  • Don't touch what you weren't asked to touch — not variable names, not comments, not import order.
  • Match the existing style exactly: quotes, casing, semicolons, indentation.
  • Clean up after yourself only: remove imports/variables/functions made unused by your change. Leave pre-existing dead code alone.
  • Don't reformat. Don't run a linter on a file that wasn't formatted with that linter.

Read the full file on GitHub · 91 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. 7d ago First seen · 91 lines · 1,159 tokens per session scan A 9ec0b5edc919

Subscribe to this mod's changes

ai-dev-playbook CLAUDE.md is an instructions file published in the GitHub repository Geeksfino/ai-dev-playbook (2 stars, last pushed 29d ago), licensed MIT. It adds 1,159 tokens to every session, about $0.0058 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

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

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

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens