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.
/plugin marketplace add softaworks/agent-toolkitnpx agentmods add plugins/softaworks/agent-toolkit/marketplacegit clone --depth 1 https://github.com/softaworks/agent-toolkitGrade A, and why
agent-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 yesterday.
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 — 927 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "agent-toolkit",
"owner": {
"name": "softaworks",
"url": "https://github.com/softaworks"
},
"metadata": {
"description": "Skills, agents, and commands for AI coding agents - individually selectable",
"version": "1.0.10"
},
"plugins": [
{
"name": "codex",
"description": "Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.",
"source": "./dist/plugins/codex",
"strict": false,
"skills": [
"./skills/codex"
],
"category": "ai-tools",
"keywords": [
"ai",
"code-analysis",
"gpt",
"codex",
"openai"
]
},
{
"name": "gemini",
"description": "Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.",
"source": "./dist/plugins/gemini",
"strict": false,
"skills": [
"./skills/gemini"
],
"category": "ai-tools",
"keywords": [
"ai",
"code-review",
"large-context",
"gemini",
"google"
]
},
{
"name": "perplexity",
"description": "Web search and research using Perplexity AI. Use when user says 'search', 'find', 'look up', 'ask', 'research', or 'what's the latest' for generic queries.",
"source": "./dist/plugins/perplexity",
"strict": false,
"skills": [
"./skills/perplexity"
],
"category": "ai-tools",
"keywords": [
"ai",
"search",
"research",
"perplexity"
]
},
{
"name": "agent-md-refactor",
"description": "Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction filesWhat 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.
- yesterday First seen · 927 lines scan A f55136f3654c
agent-toolkit is a plugin published in the GitHub repository softaworks/agent-toolkit (2,401 stars, last pushed 5mo 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
probity
Plugin marketplace listing 1 plugin: probity.
anycap
Multimodal capabilities for AI agents through the AnyCap CLI.
maptiler-skills
Plugin marketplace listing 1 plugin: maptiler.
flutter-skills
Plugin marketplace listing 1 plugin: flutter.
anotifier
Desktop & phone notifications for AI coding agents in VS Code and CLI. Supports Claude Code, Codex, Gemini CLI, and Cursor.
playwright
Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.