A runtime security add-on for AI agents that controls risky actions and records what happens.

Use it to enforce security policies around agent actions, including guidance based on OWASP MCP, ASI, and agent-skill security risks.

It can stop destructive operations, require human approval for high-risk work, and provide an audit trail for later review.

reins — Plugin for Claude Code by pegasi-ai

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/pegasi-ai/reins

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/pegasi-ai/reins/plugin/github.svg)](https://agentmods.dev/plugins/pegasi-ai/reins/plugin)

Your own site

<a href="https://agentmods.dev/plugins/pegasi-ai/reins/plugin"><img src="https://agentmods.dev/badge/plugins/pegasi-ai/reins/plugin/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/pegasi-ai/reins/plugin"><img src="https://agentmods.dev/badge/plugins/pegasi-ai/reins/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 1 skill cost 58 tokens a session between them.

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.

Security

Grade A, and why

reins 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.

plugin/.claude-plugin/plugin.json · 23 lines

What it actually says

{
  "name": "reins",
  "description": "Runtime security for AI agents. Blocks destructive actions before execution, routes high-risk operations through human approval, and maintains an immutable audit trail. Covers OWASP MCP Top 10, ASI Top 10, and Agentic Skills Top 10.",
  "version": "0.0.23",
  "author": {
    "name": "Pegasi"
  },
  "homepage": "https://app.pegasi.ai",
  "repository": "https://github.com/pegasi-ai/reins",
  "license": "Apache-2.0",
  "skills": "./skills",
  "hooks": "./hooks/hooks.json",
  "keywords": [
    "security",
    "ai-agents",
    "human-in-the-loop",
    "audit",
    "governance",
    "owasp",
    "policy-enforcement"
  ]
}

Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 58 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Skill reins C 58 tokens

Files

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.

marketplace.json 546 B

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.

1mo ago First seen · 23 lines scan A b95952596d7b

Subscribe to this mod's changes

reins is a plugin published in the GitHub repository pegasi-ai/reins (392 stars, last pushed 5d ago), licensed Apache-2.0. 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.

AI Safety Building agents Security agent-security audit-trail browser-automation cua human-in-the-loop

signet

Cryptographic signing for every AI agent tool call — Ed25519 receipts + hash-chained audit log.

Prismer-AI/signet · not measured

ethicore-guardian

Runtime AI-threat screening for Claude: analyze prompts, scan tool calls and outputs, and vet documents before you act, with BLOCK / CHALLENGE / ALLOW verdicts. Paid feature — needs a Pro-plan-or-higher Guardian API key.

OraclesTech/guardian-sdk · not measured

aria-knowledge

ARIA — Applied Reasoning and Insight Architecture. Persistent human-governed knowledge for Claude Code via a five-phase lifecycle: capture → govern → promote → apply → refresh. Stages session insights/decisions/feedback into review backlogs, promotes approved items to a tag-indexed markdown base, and applies them via…

mikeprasad/aria-knowledge · not measured

reins