agent-coding-setup: Instructions file for Claude Code

CLAUDE.md

agent-coding-setup CLAUDE.md is an instructions file for Claude Code from michaelcjoseph/agent-coding-setup. It costs 978 tokens per session, scanned A, original, MIT.

A project template for Claude Code, an AI coding assistant. It includes project instructions, separate helper agents for tasks such as testing and review, a work process, and a place for project specifications and task lists.

In plain words
What is it for?
Use it when setting up a new coding project with Claude Code, documenting its conventions, organising helper agents, running the work process, and storing project plans.
Why use it?
An AI coding assistant needs project-specific rules and a repeatable way to move from a plan to tested, reviewed code. The template provides that starting structure, which must then be adapted to the real project.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is michaelcjoseph/agent-coding-setup's own configuration. It tells Claude Code how to work on agent-coding-setup 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 agent-coding-setup configures →

Reuse

Borrowing it

Nothing to install: this file belongs to michaelcjoseph/agent-coding-setup. 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/michaelcjoseph/agent-coding-setup/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/michaelcjoseph/agent-coding-setup

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 agent-coding-setup CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/michaelcjoseph/agent-coding-setup/claude-md/github.svg)](https://agentmods.dev/instructions/michaelcjoseph/agent-coding-setup/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/michaelcjoseph/agent-coding-setup/claude-md"><img src="https://agentmods.dev/badge/instructions/michaelcjoseph/agent-coding-setup/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.

agentmods 80×15 button for agent-coding-setup CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/michaelcjoseph/agent-coding-setup/claude-md"><img src="https://agentmods.dev/badge/instructions/michaelcjoseph/agent-coding-setup/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 978 This file is loaded in full into every session.
When invoked 978 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 $0.00978 $0.00978
Opus 5.5 $0.00391 $0.00391
Sonnet 5.5 $0.00196 $0.00196
Haiku 4.5 $0.00098 $0.00098

Measured 2mo ago against content hash c1c7aeef1e3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-coding-setup 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 · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This repository is a template for dropping a consistent Claude Code setup into any new coding project — a set of review/test/docs agents, a /work skill that drives tasks through plan → implement → test → review → simplify, and a docs/projects/ scaffold for specs and task lists.

When this template is copied into a real project, replace this file with a project-specific CLAUDE.md. The agents and the /work skill read CLAUDE.md to pick up project conventions, so the more specific the real CLAUDE.md is, the better the agents behave.

Using This Template

  1. Copy the contents of this repo into the new project root (preserving .claude/ and docs/).
  2. Replace this CLAUDE.md with one that documents the real project — see "What to put in the project's CLAUDE.md" below.
  3. Replace the README.md with the project's own.
  4. Add real projects under docs/projects/NN-name/ using docs/projects/templates/ as the starting point.
  5. Delete this file's "Using This Template" and "What to put in the project's CLAUDE.md" sections once the project has its own content.

What to put in the project's CLAUDE.md

The agents and /work skill expect the real CLAUDE.md to cover:

  • Project overview — one paragraph on what the project does.
  • Architecture — major subsystems, how they fit together, entry points.
  • Project structure — directory tree of the main source folder with short comments. docs-sync updates this automatically.
  • Language / stack — language, runtime, build system, test framework.
  • Key conventions — import style, config access, logging, centralized wrappers (the project's equivalents of "all HTTP calls go through src/http.ts"). The code-reviewer and architecture-reviewer enforce these.
  • Running — how to run, test, and build. docs-sync keeps this synced with the project manifest.
  • Environment variables — list with short descriptions.
  • Agents — table of agents in .claude/agents/ and what they do. docs-sync keeps this synced.
  • Skills — table of skills in .claude/skills/ and what they do.
  • Threat model / security notes — public vs private repo, sensitive assets, trust boundaries. The security-auditor reads this.

Read the full file on GitHub · 60 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. 2mo ago First seen · 60 lines · 978 tokens per session scan A c1c7aeef1e3a

Subscribe to this mod's changes

agent-coding-setup CLAUDE.md is an instructions file published in the GitHub repository michaelcjoseph/agent-coding-setup (2 stars, last pushed 6mo ago), licensed MIT. It adds 978 tokens to every session, about $0.0039 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.

Related

agent-coding-setup CLAUDE.md compared with instructions from other repositories

agent-coding-setup CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agent-coding-setup CLAUDE.mdmichaelcjoseph/agent-coding-setupInstructions file26mo agoMITA978Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file282k3d agoMITA4,335Codex, OpenCode