generate-toolkit

generate-toolkit is a command for Claude Code from GoogilyBoogily/googilyboogily-claude-power-tools. It costs 24 tokens per session (4,054 once invoked), scanned A, original, MIT.

A project analysis command that creates tailored development skills and specialist assistants based on the tools and needs it finds in a codebase.

In plain words
What is it for?
Use it to inspect a project and generate focused helpers for areas such as testing or prompt engineering, or a broader development toolkit.
Why use it?
It helps avoid maintaining a fixed toolkit that does not match the project, while accounting for tools and guidance that already exist.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Part of the meta-toolkit plugin — 2 skills, 1 command shipped together

Good fit Use it to inspect a project and generate focused helpers for areas such as testing or prompt engineering, or a broader development toolkit.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/googilyboogily/googilyboogily-claude-power-tools/generate-toolkit
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.

Clone the repo
git clone --depth 1 https://github.com/GoogilyBoogily/googilyboogily-claude-power-tools

Made for: Claude Code.

Or install meta-toolkit, the plugin that ships this one along with the rest of its 2 skills, 1 command.

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 generate-toolkit

README.md
[![agentmods](https://agentmods.dev/badge/commands/googilyboogily/googilyboogily-claude-power-tools/generate-toolkit/github.svg)](https://agentmods.dev/commands/googilyboogily/googilyboogily-claude-power-tools/generate-toolkit)
Your own site
<a href="https://agentmods.dev/commands/googilyboogily/googilyboogily-claude-power-tools/generate-toolkit"><img src="https://agentmods.dev/badge/commands/googilyboogily/googilyboogily-claude-power-tools/generate-toolkit/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 generate-toolkit

Your own site · 80×15
<a href="https://agentmods.dev/commands/googilyboogily/googilyboogily-claude-power-tools/generate-toolkit"><img src="https://agentmods.dev/badge/commands/googilyboogily/googilyboogily-claude-power-tools/generate-toolkit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,054 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00024 $0.04054
Opus 5 $0.00012 $0.02027
Sonnet 5 $0.00005 $0.00811
Haiku 4.5 $0.00002 $0.00405

Measured 9d ago against content hash 58d881d14e5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

generate-toolkit 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 9d 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.

plugins/meta-toolkit/commands/generate-toolkit.md · 374 lines

How it starts

The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate Project Development Toolkit

Dynamically derive and generate Claude Code Skills and Subagents tailored to THIS project. Rather than producing a fixed set of artifacts, analyze what the project IS and reason about what tooling it NEEDS.

Focus area: $ARGUMENTS

  • If provided, narrow analysis and generation to artifacts relevant to this focus (e.g., "testing" generates only test-related artifacts; "prompt engineering" generates only AI/prompt-related artifacts)
  • If empty, perform full analysis across all project dimensions

Phase 0: Ecosystem Audit

Before analyzing the project, catalog what ALREADY exists. Use parallel Task subagents:

Agent A: User-Level Inventory

Scan and catalog:

  • ~/.claude/agents/ (and subdirectories) — all user-level subagents
  • ~/.claude/skills/ — all user-level skills
  • ~/.claude/commands/ — all user-level commands

For each, record: name, purpose (from description/frontmatter), tools (if subagent), category (infer from name/description)

Agent B: Project-Level Inventory

Scan and catalog:

  • .claude/agents/ — any existing project-level subagents
  • .claude/skills/ — any existing project-level skills
  • .claude/commands/ — any existing project-level commands

For each, record: name, purpose, tools (if subagent), category (infer from name/description)

Output: Ecosystem Catalog

Produce a structured catalog grouping existing capabilities by categories derived from the actual findings. Do NOT use a predefined category list — let the discovered agents/skills determine what categories exist.

For each category:

  • List the agents/skills that cover it
  • Note their scope: generic (works on any project) vs project-specific (references this project's paths/commands)

This catalog is the foundation for ALL subsequent phases. Nothing gets generated that duplicates a cataloged capability.


Phase 1: Project Intelligence

Gather project signals using parallel Task subagents:

Read the full file on GitHub · 374 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. 9d ago First seen · 374 lines · 24 tokens per session scan A 58d881d14e5e

Subscribe to this mod's changes

generate-toolkit is a command published in the GitHub repository GoogilyBoogily/googilyboogily-claude-power-tools (2 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 4,054 once invoked, about $0.0001 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 2026-09-03.