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 ulises-jeremias/agent-toolkitnpx agentmods add plugins/ulises-jeremias/agent-toolkit/agent-toolkit-agentsgit clone --depth 1 https://github.com/ulises-jeremias/agent-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/ulises-jeremias/agent-toolkit/agent-toolkit-agents)<a href="https://agentmods.dev/plugins/ulises-jeremias/agent-toolkit/agent-toolkit-agents"><img src="https://agentmods.dev/badge/plugins/ulises-jeremias/agent-toolkit/agent-toolkit-agents.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
agent-toolkit-agents 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.
What it actually says
{
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
"name": "agent-toolkit-agents",
"version": "1.25.0",
"description": "18 AI agent personas: 11 holistic (planner, architect, designer, implementer, reviewer, qa-engineer, security-engineer, platform-engineer, researcher, data-engineer) + orchestrator (assistant, client-workflow-bootstrap) + 5 specialists (code-reviewer, agentic-security-reviewer, security-reviewer, e2e-runner, tdd-guide, build-error-resolver) — 7 specialists archived to references in #865 (typescript/database/performance/refactor → reviewer/references/*; docs/reference-lookup → researcher/references/LOOKUP_GUIDE.md; tech-assistant → platform-engineer/references/WORKSTATION_OPS.md) — see docs/AGENT_TAXONOMY.md §8.",
"author": {
"name": "ulises-jeremias",
"email": "[email protected]",
"url": "https://github.com/ulises-jeremias/agent-toolkit"
},
"homepage": "https://github.com/ulises-jeremias/agent-toolkit",
"repository": "https://github.com/ulises-jeremias/agent-toolkit",
"license": "MIT",
"keywords": [
"agent-toolkit",
"agents"
]
}
What it installs
The manifest is a name and a version. 18 agents travel with it, and installing the plugin installs all of them — 1,029 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Agent designer A 78 tokens
- Agent tdd-guide A 53 tokens
- Agent platform-engineer A 88 tokens
- Agent researcher A 60 tokens
- Agent agentic-security-reviewer A 72 tokens
- Agent assistant A 35 tokens
- Agent data-engineer A 55 tokens
- Agent implementer A 62 tokens
- Agent qa-engineer A 66 tokens
- Agent reviewer A 51 tokens
- Agent security-engineer A 65 tokens
- Agent client-workflow-bootstrap A 57 tokens
- Agent architect A 28 tokens
- Agent build-error-resolver A 62 tokens
- Agent code-reviewer A 45 tokens
- Agent e2e-runner A 64 tokens
- Agent planner A 32 tokens
- Agent security-reviewer A 56 tokens
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 · 19 lines scan A 3d9f3b54c856
agent-toolkit-agents is a plugin published in the GitHub repository ulises-jeremias/agent-toolkit (16 stars, last pushed 5d 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
humanize-writing
Remove documented AI-writing patterns from generated and existing text, with register awareness and voice calibration.
skraft
skraft SDLC pipeline — agents, skills and instructions for outside-in TDD, Clean Architecture and the DISCOVER→DELIVER workflow.
LogoLoom
AI-powered logo design → SVG → full brand kit. Free, local, MCP-native.
mosaic-bridge
Mosaic Bridge — Unity MCP assistant agents for scene building, shader creation, and session continuity.
matlab-slash-commands
Slash commands for MATLAB development workflows — documentation, testing, optimization, code analysis, and MCP integration.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.