coding-agent-fabric CLAUDE.md

coding-agent-fabric CLAUDE.md is an instructions file for coding agents from yu-iskw/coding-agent-fabric. It costs 1,353 tokens per session, scanned A, original, Apache-2.0.

A project guide for a TypeScript monorepo—a codebase that holds several related packages in one repository. It records the project layout, commands, coding rules, and testing practices for Claude Code.

In plain words
What is it for?
Use it when asking Claude Code to work on this TypeScript project, especially to install dependencies, build packages, run Vitest tests, lint, format, or prepare changes for commit.
Why use it?
It gives the coding agent the project context needed to follow the repository’s existing conventions. This reduces guesswork about commands, file names, formatting, and tests.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/yu-iskw/coding-agent-fabric/claude-md
Clone the repo
git clone --depth 1 https://github.com/yu-iskw/coding-agent-fabric

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 coding-agent-fabric CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yu-iskw/coding-agent-fabric/claude-md.svg)](https://agentmods.dev/instructions/yu-iskw/coding-agent-fabric/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/yu-iskw/coding-agent-fabric/claude-md"><img src="https://agentmods.dev/badge/instructions/yu-iskw/coding-agent-fabric/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,353 This file is loaded in full into every session.
When invoked 1,353 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01353 $0.01353
Opus 5 $0.00677 $0.00677
Sonnet 5 $0.00271 $0.00271
Haiku 4.5 $0.00135 $0.00135

Measured 4d ago against content hash 10be1736b733, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coding-agent-fabric 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.

CLAUDE.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TypeScript Monorepo - Claude Code Memory

Project Overview

This is a production-ready TypeScript monorepo template using modern tooling:

  • Package Manager: pnpm (with workspace support)
  • Runtime: Node.js (see .node-version for current version)
  • Build System: tsc / pnpm
  • Linting/Formatting: Trunk (manages ESLint, Prettier, and more)
  • Testing: Vitest
  • CI/CD: GitHub Actions

Quick Commands

pnpm install    # Install all dependencies
pnpm build      # Build all packages
pnpm test       # Run all tests via Vitest
pnpm lint       # Run all linters via Trunk
pnpm format     # Auto-format code via Trunk
pnpm clean      # Clean build artifacts

Code Style

  • Use TypeScript for all code
  • Follow project ESLint/Prettier configuration (managed via Trunk)
  • Use functional programming patterns where appropriate
  • Use PascalCase for classes/interfaces, camelCase for functions/variables
  • Use kebab-case for file names (e.g., user-service.ts)

Testing

  • Write tests in tests/ or alongside source files as *.test.ts
  • Use Vitest for unit and integration tests
  • Aim for high test coverage on core logic
  • Run pnpm test before committing

Git Workflow

  • Create feature branches from main
  • Run pnpm lint && pnpm test before commits
  • Commit messages: type(scope): description (e.g., feat(ui): add new button component)
  • Types: feat, fix, docs, style, refactor, test, chore
  • Record changes using the manage-changelog skill when changie is available

Architecture

  • Source code in packages/* or src/ (depending on package structure)
  • Development scripts and shared config in root
  • CI/CD workflows in .github/workflows/
  • Claude Code configuration in .claude/
  • Document significant design decisions as Architecture Decision Records (ADRs) in docs/adr; use the manage-adr skill when adr is available

Common Gotchas

  • Always use pnpm instead of npm or yarn
  • Trunk manages tool versions hermetically - don't install linters globally
  • The pnpm-lock.yaml file is committed for reproducibility - don't gitignore it
  • Run trunk install if linters report missing tools

Read the full file on GitHub · 120 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. 4d ago First seen · 120 lines · 1,353 tokens per session scan A 10be1736b733

Subscribe to this mod's changes

coding-agent-fabric CLAUDE.md is an instructions file published in the GitHub repository yu-iskw/coding-agent-fabric (1 stars, last pushed 19d ago), licensed Apache-2.0. It adds 1,353 tokens to every session, about $0.0068 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.