# SigmaShake Documentation
> Complete documentation for SigmaShake — governance rules for AI agents

## What is SigmaShake?
SigmaShake is a rule engine that evaluates AI agent tool calls against declarative governance rules before execution. Sub-2 ms enforcement at the tool-call boundary, including FORCE safe alternatives.

## Documentation Pages
- Introduction: https://docs.sigmashake.com/
- Getting Started: https://docs.sigmashake.com/getting-started
- Agent Install Guide: https://docs.sigmashake.com/agent-install-guide
- Agent skill: https://docs.sigmashake.com/agent-skill
- Agent skill (raw markdown): https://docs.sigmashake.com/skills/sigmashake/SKILL.md
- Rule Syntax Reference: https://docs.sigmashake.com/rule-syntax
- Operator Reference: https://docs.sigmashake.com/operators
- Field Reference: https://docs.sigmashake.com/fields
- CLI Reference: https://docs.sigmashake.com/cli
- Dashboard Guide: https://docs.sigmashake.com/dashboard
- MCP Server: https://docs.sigmashake.com/mcp
- Grok Bot / SigmaShake Guardrails: https://docs.sigmashake.com/grok-bot
- Architecture: https://docs.sigmashake.com/architecture
- Client Adapters: https://docs.sigmashake.com/adapters
- Evaluation Deep Dive: https://docs.sigmashake.com/evaluation
- Writing Rules Guide: https://docs.sigmashake.com/writing-rules
- Claude Code Integration: https://docs.sigmashake.com/claude-code-integration
- Rules Hub: https://docs.sigmashake.com/hub

## Platform Components
- Landing page: https://sigmashake.com
- Rules Hub (browse/search/download rules): https://hub.sigmashake.com
- Hub JSON API: https://hub.sigmashake.com/api/rulesets
- MCP Server Streamable HTTP (Grok Bot hosted default): https://mcp.sigmashake.com/mcp
- MCP Server local stdio (Grok Bot when ssg reachable): ssg mcp-server --client=grok-bot
- MCP Server SSE (legacy): https://mcp.sigmashake.com/sse
- Grok Bot install: https://grok.sigmashake.com
- OpenAPI spec: https://mcp.sigmashake.com/api/openapi.json
- Source code: https://github.com/sigmashakeinc/ssg
- Docker image: https://github.com/orgs/sigmashakeinc/packages/container/package/ssg

## Install
Agents (no TTY) — the consent flag is required, or the installer fails closed:
```bash
curl -fsSL https://install.sigmashake.com | sh -s -- -y
```
Then follow https://docs.sigmashake.com/agent-install-guide (`ssg_onboard`, or `ssg init --smart --client=<host>`).
Human install: `curl -fsSL https://install.sigmashake.com | sh`
Docker / GHCR: `docker run --rm ghcr.io/sigmashakeinc/ssg:1.0.7 --version`

## MCP Integration
```json
{"mcpServers": {"sigmashake-guardrails": {"type": "streamable-http", "url": "https://mcp.sigmashake.com/mcp"}}}
```

## Rule Syntax (Quick Reference)
```
rule block-dangerous-commands {
  priority 100
  severity error
  DENY execution
  IF command CONTAINS "rm -rf"
  MESSAGE "Destructive command blocked."
}
```

Fields: command, path, content, tool, input.<key>
Operators: CONTAINS, EQUALS, STARTS_WITH, ENDS_WITH, GLOB, REGEX, WORD, LINE_CONTAINS, LINE_REGEX
Decisions: ALLOW, DENY (runtime: block), ASK, FORCE, LOG, SHADOW
FORCE refuses the original risky action and returns a safe substitute or required safer path for the agent to use next.
Targets: execution, read, write, edit, search, agent, network, any

## Pricing
- Free to download and install; Pro is required to use governance eval, dashboard, hub rule bodies, metering, and other value surfaces. No free tier, no trial.
- **Pro**: $5/mo. Unlimited Tool Evaluations, cloud audit sync, private rulesets, AI rule generation, priority email support
- **Enterprise**: Custom. Everything in Pro plus extended audit retention, SSO/SAML, team policy sharing, on-prem deployment, custom adapter development, dedicated support