agent-alchemy CLAUDE.md

agent-alchemy CLAUDE.md is an instructions file for coding agents from sequenzia/agent-alchemy. It costs 4,774 tokens per session, scanned A, original, MIT.

Project instructions for Agent Alchemy, a monorepo—a single repository containing several related projects—that extends Claude Code with plugins, a task dashboard, and a VS Code extension.

In plain words
What is it for?
Working on its Claude Code plugins, code-analysis tools, test-driven development workflows, Git tools, dashboard, and editor extension.
Why use it?
They explain the repository layout and development conventions so an assistant can work in the right part of the larger codebase.

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/sequenzia/agent-alchemy/claude-md
Clone the repo
git clone --depth 1 https://github.com/sequenzia/agent-alchemy
Per session 4,774 This file is loaded in full into every session.
When invoked 4,774 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 $0.04774 $0.04774
Opus 5 $0.02387 $0.02387
Sonnet 5 $0.00955 $0.00955
Haiku 4.5 $0.00477 $0.00477

Measured 3d ago against content hash cee083ad6ce9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-alchemy 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 3d 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 · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Overview

Agent Alchemy is a monorepo that extends Claude Code into a structured development platform through markdown-as-code plugins, a real-time task dashboard, and a VS Code extension.

Repository Structure

agent-alchemy/
├── claude/                    # Claude Code plugins (markdown-as-code)
│   ├── .claude-plugin/        # Plugin marketplace registry
│   ├── claude-tools/          # Claude Code Tasks & Agent Teams reference skills
│   ├── core-tools/            # Codebase analysis, deep exploration, language patterns (includes hooks/)
│   ├── dev-tools/             # Feature dev, debugging, code review, docs, changelog
│   ├── sdd-tools/             # Spec-Driven Development pipeline
│   ├── tdd-tools/             # TDD workflows: test generation, RED-GREEN-REFACTOR, coverage
│   ├── git-tools/             # Git commit automation
│   ├── plugin-tools/          # Plugin porting, adapter validation, ported plugin maintenance, ecosystem health
│   ├── opencode-tools/        # OpenCode extension creation, update, and validation toolkit
│   └── cs-tools/              # Competitive programming problem-solving and solution verification
├── agent-tools/               # Python CLI for cross-harness skill management (Typer)
├── apps/
│   └── task-manager/          # Next.js 16 real-time Kanban dashboard
├── extensions/
│   └── vscode/                # VS Code extension for plugin authoring
├── internal/docs/             # Internal documentation and analysis
└── site/                      # MkDocs documentation site (generated)

Development Commands

# Task Manager
pnpm dev:task-manager          # Start dev server on port 3030
pnpm build:task-manager        # Production build

# VS Code Extension
cd extensions/vscode
npm install
npm run build                  # Build with esbuild
npm run watch                  # Watch mode
npm run package                # Package VSIX

# Agent Tools CLI
cd agent-tools
uv sync                        # Install dependencies
uv run agent-tools --help      # Run CLI
uv run pytest                  # Run tests (~295 tests)
uv run ruff check .            # Lint

# Linting
pnpm lint                      # Lint all packages

Read the full file on GitHub · 262 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. 3d ago First seen · 262 lines · 4,774 tokens per session scan A cee083ad6ce9

Subscribe to this mod's changes

agent-alchemy CLAUDE.md is an instructions file published in the GitHub repository sequenzia/agent-alchemy (43 stars, last pushed 3mo ago), licensed MIT. It adds 4,774 tokens to every session, about $0.0239 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.