What is agentready CLAUDE.md?

A repository guide that gives AI agents an overview of a TypeScript project. It records the project files, package manager, source layout, build and test setup, and whether the repository uses a monorepo, meaning several packages managed together.

Use it to find likely entry files, inspect TypeScript settings, understand the package structure, check deployment-related files, and locate the README.

It saves time spent searching through the repository before making changes. It also makes missing tools or configuration visible, such as the absence of tests, bundling tools, or continuous-integration workflows.

agentready CLAUDE.md — Instructions file by makalin

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/makalin/agentready/claude-md

Clone the repo

git clone --depth 1 https://github.com/makalin/agentready

Per session 508 This file is loaded in full into every session.

When invoked 508 The same file — it is already loaded in full.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.00508	$0.00508
Opus 5	$0.00254	$0.00254
Sonnet 5	$0.00102	$0.00102
Haiku 4.5	$0.00051	$0.00051

Measured 2d ago against content hash 328e79d5a179, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

agentready CLAUDE.md scanned grade C 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

| `npm run clean` | rm -rf dist |

CLAUDE.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agentready — agent context

Overview

High-fidelity repository context for AI agents — generates CLAUDE.md and CONTRIBUTING.md from your codebase.

Stack & tooling

TypeScript (tsconfig present)

Repository landmarks

Root: /Users/makalin/Public/htdocs/agentready
Nearest package.json: package.json
TypeScript config: tsconfig.json
ESLint: none detected
Prettier: none detected

Top-level directories

src/

Likely entry / index files (sample)

src/index.ts

Source files by extension

.ts: 16 file(s)

Total scanned source files: 16

Shipping, CI, and environments

Package manager

npm — install with npm install

Monorepo

No (single package at root, or no workspaces field).

Continuous integration (GitHub Actions)

No GitHub Actions workflows under .github/workflows.

Containers

No Dockerfile or compose files matched common path patterns.

Environment templates

No .env.example / .env.sample files detected.

Quality and build tooling

No common test or bundler packages detected in package.json dependencies.

README: README.md

TypeScript compiler options (summary)

strict: true
module: commonjs
target: ES2022

Commands agents should use

Use the project’s real scripts where they exist:

Script	Command
`npm run build`	tsc
`npm run agentready`	node dist/cli.js
`npm run clean`	rm -rf dist
`npm run prepack`	npm run build

Guardrails for agents

Prefer existing patterns, naming, and folder layout over new conventions.
Run the test and lint scripts from package.json after non-trivial edits when those scripts exist.
Do not commit secrets, .env files, or credentials.
Respect .gitignore; generated folders like node_modules and dist are out of scope unless the task explicitly requires them.

Generated by AgentReady. Re-run agentready build after major structural changes.

Read the full file on GitHub · 89 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.

2d ago First seen · 89 lines · 508 tokens per session scan C 328e79d5a179

Subscribe to this mod's changes

agentready CLAUDE.md is an instructions file published in the GitHub repository makalin/agentready (2 stars, last pushed 5mo ago), licensed MIT. It adds 508 tokens to every session, about $0.0025 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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

agentready CLAUDE.md