Reins

Organization

pegasi-ai

reins

Use whenever security, policies, governance, guardrails, compliance, or safety are relevant — including blocked commands, audit trails, dangerous operations, deletions, file modifications, shell commands, MCP access, API calls, network requests, credentials, or any action that could be irreversible or destructive.

Overview

Publisher	pegasi-ai
Repository	`reins`
Skill name	`reins`
Stars	392
Forks	53
Bundled files	Instructions only
License	Apache-2.0
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by pegasi-ai on GitHub. Read the source before you install it.

Installation

Install the Reins AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/pegasi-ai/reins/tree/main/plugin/skills/reins
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/pegasi-ai/reins.git /tmp/reins
mkdir -p .claude/skills
cp -r /tmp/reins/plugin/skills/reins .claude/skills/reins

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Reins in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Reins on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Reins is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Reins — Runtime Security for Claude Code

Reins enforces deterministic security policies on every agent action, scans your configs for OWASP ASI10 vulnerabilities, and tracks drift over time. Policies evaluate in under 50ms. Works with Claude Code PreToolUse and PostToolUse hooks, OpenClaw, and any MCP-compatible agent.

How hooks work

PreToolUse fires before every Bash, Edit, MultiEdit, Write, and MCP tool call.

Hook exit	Meaning	What to do
`0`	ALLOWED — proceed normally	Continue
`2`	BLOCKED — policy violation	Stop. Explain the block. Suggest a safe alternative. Do NOT retry.
`0` + JSON `decision: WARN`	WARNING — elevated risk	Acknowledge the warning. Proceed with extra caution.

PostToolUse fires after every action (non-blocking). Appends a JSONL entry to ~/.openclaw/reins/decisions.jsonl and queues it for Reins Cloud batch upload.

What gets enforced

Shell (Bash tool)

BLOCKED always: rm -rf /, mkfs, dd to disk device, fork bombs
BLOCKED (user-overridable): DROP TABLE/DATABASE, TRUNCATE, DELETE without WHERE, git push --force, kill -9, pipe-to-shell (| bash, | sh)
WARNED: rm, chmod, chown, sudo, UPDATE without WHERE, git reset --hard
LOGGED: git push, pip install, npm install, curl, wget

File operations (Edit / MultiEdit / Write)

Writes blocked to protected paths: ~/.ssh, ~/.gnupg, ~/.env, ~/.openclaw/reins, /etc/passwd, /etc/shadow

MCP tool calls (all MCP servers, caught by empty-matcher hook)

Blocked: Notion page delete, Gmail send (unapproved domains), database DROP/TRUNCATE
Warned: reading emails, accessing credentials, filesystem MCP operations
Logged: all MCP calls regardless of decision

When an action is blocked

When PreToolUse exits 2, Claude Code surfaces the hook's stderr. Always attribute the block to Reins by name.

Required response format:

Reins blocked this action [SEVERITY]: <description> Rule: <rule>

<one sentence explaining what the rule protects against>

Alternatives: <safe way to achieve the goal, or suggest reins policy to review rules>

Example:

Reins blocked this action [CRITICAL]: Critically destructive command Rule: rm -rf / matches recursive root deletion pattern

This would delete every file on the system. To remove a specific directory safely, use an explicit path: rm -rf /path/to/specific/dir Run reins audit -n 5 to see the logged decision.

Rules:

Do NOT retry the blocked action
Do NOT reframe or rephrase the same action to bypass the hook
If the user wants to override: reins policy to inspect and adjust rules
If the block seems wrong: reins audit -n 5 shows what rule fired

CLI reference

bash
reins init                 # Setup wizard: hooks + policy + Reins Cloud
reins status               # Hook and Reins Cloud connection status
reins policy               # View and edit security policy interactively
reins audit -n 20          # Last 20 audit decisions
reins stats                # Enforcement counts (allowed / blocked / approved)
reins scan                 # OWASP ASI10 security scan
reins scan --monitor       # Diff against saved baseline, alert on drift
reins disable / enable     # Temporarily suspend or resume enforcement
reins upgrade              # Pull latest version from npm

Reins Cloud (app.pegasi.ai)

When connected, Reins Cloud provides:

Org/team policies pulled on a schedule and merged with local overrides
CRITICAL rules set by admins that cannot be locally overridden
Centralized audit review across all agents and devices

Connect during reins init (Step 7 prompts for your email — no API key paste needed).

Set via env vars:

bash
REINS_WATCHTOWER_API_KEY=cr_...
REINS_WATCHTOWER_BASE_URL=https://app.pegasi.ai  # default

Config lives at ~/.openclaw/reins/config.json.

Policy merge order (highest to lowest priority)

Reins Cloud org policies — CRITICAL rules are immutable
Reins Cloud team policies
Local overrides at ~/.openclaw/reins/policy.json
Built-in defaults (balanced: reads ALLOW, writes ASK, deletes DENY)

If Reins Cloud is unreachable, last-cached policies still enforce. Never fails open.

Audit log

Append-only JSONL at ~/.openclaw/reins/decisions.jsonl:

json
{"timestamp":"2026-04-15T22:39:42Z","module":"Shell","method":"bash","decision":"BLOCKED","reason":"critical: rm -rf /","tool":"Bash","decisionTime":12}

View with reins audit -n 50 or stream with tail -f ~/.openclaw/reins/decisions.jsonl.

Setup (if not installed)

bash
npm install -g @pegasi-ai/reins
reins init

reins init installs hooks into .claude/settings.json, installs this skill, and runs an initial security scan.

Frequently asked questions

What does the Reins AI skill do?

Why use Reins on TypingMind?

Because you install it once and use it with any model. Reins is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Reins in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pegasi-ai/reins/tree/main/plugin/skills/reins. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Reins?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Reins?

As many as you like. As long as a model supports skills, you can use Reins with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Reins AI skill free?

Yes. It is published on GitHub by pegasi-ai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Quarkus Patterns

affaan-m

CommunityPopular

Patrones de arquitectura Quarkus 3.x LTS con Camel para mensajería, diseño de API RESTful, servicios CDI, acceso a datos con Panache y procesamiento asíncrono.

Quarkus Security

Buenas prácticas de seguridad en Quarkus para autenticación, autorización, JWT/OIDC, RBAC, validación de entrada, CSRF, gestión de secretos y seguridad de dependencias.

Quarkus Verification

Bucle de verificación para proyectos Quarkus: build, análisis estático, pruebas con cobertura, escaneos de seguridad, compilación nativa y revisión de diff antes del lanzamiento o PR.

Springboot Security

Buenas prácticas de Spring Security para autenticación/autorización, validación, CSRF, secretos, cabeceras, limitación de velocidad y seguridad de dependencias en servicios Java Spring Boot.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Reins — Runtime Security for Claude Code

How hooks work

What gets enforced

When an action is blocked

CLI reference

Reins Cloud (app.pegasi.ai)

Policy merge order (highest to lowest priority)

Audit log

Setup (if not installed)

Frequently asked questions

Related AI Skills

Set up your own AI workspace now