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/jgamaraalv/ts-dev-kit/claude-mdgit clone --depth 1 https://github.com/jgamaraalv/ts-dev-kitWrote 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.
[](https://agentmods.dev/instructions/jgamaraalv/ts-dev-kit/claude-md)<a href="https://agentmods.dev/instructions/jgamaraalv/ts-dev-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/jgamaraalv/ts-dev-kit/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01052 | $0.01052 |
| Opus 5 | $0.00526 | $0.00526 |
| Sonnet 5 | $0.00210 | $0.00210 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
ts-dev-kit 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.
How it starts
The opening of the file, as written. The whole thing — 98 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.
Project Overview
ts-dev-kit is a Claude Code plugin (not a traditional app/library) that ships 15 specialized agents and 22 curated skills for TypeScript fullstack development. It is published to npm as @jgamaraalv/ts-dev-kit and distributed as markdown files — there is no build step, no TypeScript compilation, and no test suite.
Common Commands
# Publish to npm
npm publish --access public
# Verify what gets published
npm pack --dry-run
# Version bump (update package.json, plugin.json, marketplace.json in sync)
# All three manifests must have matching versions
There are no build, lint, or test commands — this is a content-only package.
Architecture
Content Layout
.claude/
agents/ ← 15 agent definitions (markdown, YAML frontmatter)
skills/ ← 22 skill directories (symlinked from skills/)
settings.local.json ← Permission allowlist for Claude Code
.claude-plugin/
plugin.json ← Claude Code plugin manifest
marketplace.json ← Marketplace listing metadata
agents/ ← Published copy of .claude/agents (included in npm package)
agent-memory/ ← 14 persistent memory directories (one per agent, excluded: multi-agent-coordinator (planner-only, no memory needed))
skills/ ← 22 skill directories (each has SKILL.md + optional references/ and scripts/)
Agent Definitions (.claude/agents/*.md)
Each agent is a single markdown file with YAML frontmatter:
---
name: agent-name
color: named-color # Visual identification in Claude Code UI
description: "..."
skills: # Optional — skills loaded when agent is invoked
- skill-slug
---
Body contains: role description, core principles, workflow steps, quality gates, output format, and a reference to agent-memory/<name>/MEMORY.md.
Skill Definitions (skills/<name>/)
Each skill directory contains:
SKILL.md— main content with YAML frontmatter (name,description, optionalargument-hint, optionalallowed-tools)references/— deep-dive sub-files linked from SKILL.mdscripts/— optional executables Claude can run (Python, bash) for visual output or automation
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.
- 4d ago First seen · 98 lines · 1,052 tokens per session scan A 82b4a590c47d
ts-dev-kit CLAUDE.md is an instructions file published in the GitHub repository jgamaraalv/ts-dev-kit (15 stars, last pushed 6mo ago), licensed MIT. It adds 1,052 tokens to every session, about $0.0053 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 2026-08-30.
Other instructions, from other repositories
vscode design-philosophy.instructions.md
VS Code design philosophy — the shared Values→Principles→Moves vocabulary for reasoning about UI in design terms rather than raw pixels. Use when creating, editing, or reviewing any visual surface (CSS, DOM, theming, icons, motion). Name the value/principle before reaching for a token.
deepagents AGENTS.md
AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
walkerOS CLAUDE.md
Claude Code instructions for elbwalker/walkerOS, covering claude.md and important: use agent.md.
openmcp-client CLAUDE.md
Instructions for LSTM-Kirigaya/openmcp-client, covering claude.md, development commands, setup and installation, development and service development.
Kokoro-Engine CLAUDE.md
Instructions for chyinan/Kokoro-Engine, covering claude.md, git 规范, 项目概述, 常用命令 and 安装依赖.
markdy-com copilot-instructions.md
Copilot instructions for HoangYell/markdy-com, a project described as: 🎬 Open-source animated architecture diagrams as code. Diagram-native DSL, 17 layout engines, Web Animations API, and MCP server for AI agents.