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/catpilotai/catpilot-ai-guardrailsWrote 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/catpilotai/catpilot-ai-guardrails/catpilot-ai-guardrails)<a href="https://agentmods.dev/plugins/catpilotai/catpilot-ai-guardrails/catpilot-ai-guardrails"><img src="https://agentmods.dev/badge/plugins/catpilotai/catpilot-ai-guardrails/catpilot-ai-guardrails/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/catpilotai/catpilot-ai-guardrails/catpilot-ai-guardrails"><img src="https://agentmods.dev/badge/plugins/catpilotai/catpilot-ai-guardrails/catpilot-ai-guardrails.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
catpilot-guardrails 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 today.
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": "catpilot-guardrails",
"displayName": "Catpilot Security Skills",
"version": "2026.09.18",
"description": "Two security skills in the Agent Skills format: catpilot-safe-building, eight plain-language checkpoints for a person building with an AI assistant, and catpilot-security-core, nine engineering components for coding agents. Advice the model reads. This plugin carries no hooks, no MCP servers, and no telemetry.",
"author": { "name": "Catpilot", "url": "https://catpilot.ai" },
"homepage": "https://github.com/catpilotai/catpilot-ai-guardrails",
"repository": "https://github.com/catpilotai/catpilot-ai-guardrails",
"license": "MIT",
"keywords": ["security", "guardrails", "safe-building", "skills"]
}
What it installs
The manifest is a name and a version. 19 skills travel with it, and installing the plugin installs all of them — 1,592 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill cloud-cli-safety A 92 tokens
- Skill pii-and-test-data A 97 tokens
- Skill database-safety A 75 tokens
- Skill secret-blocking A 101 tokens
- Skill catpilot-safe-building A 114 tokens
- Skill hosting-and-where-it-runs A 48 tokens
- Skill keys-and-credentials A 53 tokens
- Skill sharing-and-publishing A 51 tokens
- Skill third-party-services A 48 tokens
- Skill untrusted-input A 62 tokens
- Skill access-and-identity A 49 tokens
- Skill when-to-ask-a-human A 60 tokens
- Skill language-baseline B 115 tokens
- Skill data-in-prompts B 57 tokens
- Skill secrets-management C 103 tokens
- Skill supply-chain C 99 tokens
- Skill catpilot-security-core C 128 tokens
- Skill docker-safety D 114 tokens
- Skill local-cli-safety F 126 tokens
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.
- today First seen · 12 lines scan A d7f5b9645067
catpilot-guardrails is a plugin published in the GitHub repository catpilotai/catpilot-ai-guardrails (2 stars, last pushed today), 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 2026-09-21.
Other plugins, from other repositories
pict-test-designer
Design comprehensive test cases using PICT (Pairwise Independent Combinatorial Testing) for any piece of requirements or code. Analyzes inputs, generates PICT models with parameters, values, and constraints for valid scenarios using pairwise testing. Outputs the PICT model, markdown table of test cases, and expected…
sentinel-ai
Real-time safety scanning for LLM interactions. Detects prompt injection, PII leaks, harmful content, toxicity, obfuscation, secrets, and dangerous tool calls — 600-case benchmark at 100% accuracy with sub-millisecond latency.
multai
MultAI — Submit research prompts to 7 AI platforms simultaneously (Claude.ai, ChatGPT, Copilot, Perplexity, Grok, DeepSeek, Gemini), synthesize results, maintain capability comparison matrices, and produce landscape reports — all from Claude Code.
eterdis-market-position
Competitive positioning diagnostic — figure out where you actually stand and whether that position is defensible.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.