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.
git clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkitWrote 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/plugins/stefan-jansen/claude-code-toolkit/development)<a href="https://agentmods.dev/plugins/stefan-jansen/claude-code-toolkit/development"><img src="https://agentmods.dev/badge/plugins/stefan-jansen/claude-code-toolkit/development/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.
<a href="https://agentmods.dev/plugins/stefan-jansen/claude-code-toolkit/development"><img src="https://agentmods.dev/badge/plugins/stefan-jansen/claude-code-toolkit/development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
development 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 1mo 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.
What it actually says
{
"name": "development",
"version": "1.1.0",
"description": "Code development and quality assurance tools - analyze, test, fix, review",
"author": {
"name": "Claude Code Framework"
},
"keywords": [
"development",
"testing",
"quality",
"analysis",
"debugging",
"git"
],
"commands": [
"./commands/analyze.md",
"./commands/docs.md",
"./commands/fix.md",
"./commands/git.md",
"./commands/prepare-review.md",
"./commands/review.md",
"./commands/test.md"
],
"agents": [
"./agents/architect.md",
"./agents/code-reviewer.md",
"./agents/test-engineer.md"
],
"repository": "https://github.com/yourusername/claude-code-plugins",
"license": "MIT"
}
What it installs
The manifest is a name and a version. 7 commands, 3 agents travel with it, and installing the plugin installs all of them — 117 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 33 lines scan A f8759cb5364e
development is a plugin published in the GitHub repository stefan-jansen/claude-code-toolkit (90 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
desktop-notification
Alert you when Claude Code needs input: an audible terminal bell, an OSC 9 terminal notification, and an OS-native toast (macOS/Linux) on permission and idle prompts.
disk-hygiene
Context-aware disk hygiene for arbitrary directory trees: inventories orphaned and temporary artifacts, classifies evidence into review tiers, and offers exact-path cleanup only after a fresh safety preview and explicit per-tier approval. The target is read-only by default; OS-managed paths, links and mount points…
fleet
Agent-to-agent reach across a personal fleet (fleet:reach): from any Claude Code lane (WSL or native Windows, any machine), run a script, prompt, or query and wait, message a session, or start a named session in another lane. Each lane signs into its own Claude account, so built-in peer tools see only their own lane.…
firecrawl
Web scraping, search, crawling, and file parsing through the firecrawl-cli binary with a write-to-disk-then-Read pattern that keeps large results out of context: a user-facing wrapper skill, a lazy-install setup skill, and a separate gated maintainer update skill tracking the upstream CLI and skill source.
build-it
Autonomous delivery orchestrator for Claude Code — the build stage of the -it lifecycle (plan-it plans it, build-it builds it); formerly fable-it. Model-adaptive for Sonnet 5 and Opus 4.8. Invoke with a goal and a numbered Definition of Done; it runs the whole job to completion by conducting the bundled launch, iterat.
igpt-finance
Finance intelligence skills powered by iGPT. Extracts invoices, tracks subscriptions, builds expense reports, monitors payment status, analyzes vendor spend, and collects tax documents — all from connected email datasources.