Rule sets
Declarative .rules files that enforce policy on agent tool calls. Content-hash locked, Ed25519-signed by the author, and replayable in the playground. Install with ssg hub pull rules-typescript.
Official Rules Library · signed & versioned
Governance rules for every AI agent
Discover, fork, and install declarative .rules that enforce policy on agent tool-calls before they run. Zero‑latency, zero‑tokens. Rulesets are authored by SigmaShake; community contributions welcome.
232
Public rulesets
2.3k
Rules enforced
11
Public plugins
Most installed
Browse all
Featured rulesets
TypeScript
Official
Verified
TypeScript is a strongly typed programming language that builds on JavaScript. These rules govern type safety, vulnerability prevention, and idiomatic coding patterns for AI agents.
Github-actions
Official
Verified
GitHub Actions is a CI/CD platform that allows you to automate your build, test, and deployment pipeline. These rules govern workflow security, secret management, and action configuration for AI agents.
React
Official
Verified
React is a JavaScript library for building user interfaces based on components. These rules govern hook usage, state management, and component lifecycle best practices for AI agents.
Docker
Official
Verified
Docker is a platform for developing and running applications in containers. These rules guide AI agents in containerizing applications, managing Dockerfiles, and optimizing multi-stage builds and Docker Compose configurations.
Rust
Official
Verified
Rust is a systems programming language focused on safety, speed, and concurrency. These rules govern memory management, ownership patterns, and idiomatic Rust development for AI agents — including filesystem-safety lessons learned from the Canonical/Zellic audit of rust-coreutils (CVE-2026-35338..35381).
Windows
Official
Verified
Windows is a major family of operating systems developed by Microsoft. These rules govern system security, administrative safety, and configuration best practices for AI agents.
Find what you need
Explore by category
More than just rules
Browse plugins
Plugins: signed dashboard extensions
Plugins
Signed tarballs that extend the SSG dashboard UI. Workspace, observability, productivity panels, and more — installable on demand with ssg plugins install. Browse the marketplace.
Most installed
Browse all plugins
Featured plugins
Fresh from the marketplace
See more
Recently added plugins
Terminal
CommunityGHOSTMUX persistent terminal - tmux-style multi-session PTY with coding-agent launcher.
SigmaShake STRIKE
VerifiedUserspace AI-agent compromise monitor — live Safe/Suspicious/Compromised verdict per agent session, with behavioral signal classification and session-level risk scoring.
Slack Approvals
VerifiedApprove or deny SSG tool-call prompts from Slack — Block Kit buttons over Socket Mode (no public URL), with an approver allowlist that verifies the human.
Voice Dictation
CommunityLocal Whisper voice-to-text (whisper.cpp WASM) with a settable hotkey — dictate in the SSG dashboard or Desktop and turn speech into a .rules file.
Plan Meter
CommunityYour SSG plan tier and today's eval usage at a glance.
Mode Control
CommunitySwitch eval mode (ask/allow/deny) and dry-run tool calls against your rules.
How it works
From
From .rules to enforced policy in three steps
-
01
Discover or fork
Browse signed, versioned rulesets authored by SigmaShake — and submit your own. Each ruleset is fetched directly from GitHub and locked to a content hash.
-
02
Install with one command
Run
ssg hub pull rules-typescriptand the engine pulls, verifies the signature, and writes the ruleset into your project's.sigmashake/directory. -
03
Enforce at tool-call boundary
Every agent tool call is evaluated against the ruleset before execution — zero-latency, zero-tokens. Decisions: ALLOW, DENY, ASK, FORCE, LOG, SHADOW; FORCE returns a safe substitute path.
Latest releases
See more
Recently updated
Frontend
@sigmashakeinc/rules-frontend
Official
Verified
Jira
@sigmashakeinc/rules-jira
Official
Verified
Jira and Atlassian governance for AI assistants. These rules require human approval before an agent deletes issues or makes bulk changes across many tickets, and keep an audit trail of every create/update/comment/transition — the controls a team wants when Claude Cowork or the Codex desktop app drives Jira over MCP.
Openhands
@sigmashakeinc/rules-openhands
Official
Verified
Plandex
@sigmashakeinc/rules-plandex
Official
Verified
Sheets
@sigmashakeinc/rules-sheets
Official
Verified
Google Sheets and Microsoft Excel governance for AI assistants. These rules block spreadsheet formulas that exfiltrate data to external URLs (IMPORTXML / IMPORTDATA / IMPORTRANGE / WEBSERVICE) and require approval before an agent deletes a sheet or clears cells — the controls a non-technical user wants when an AI app is connected to their spreadsheets over MCP.
Slack
@sigmashakeinc/rules-slack
Official
Verified
Slack governance for AI assistants. These rules require human approval before an agent posts a message or pings a whole channel (@channel / @here / @everyone) and keep an audit trail of channel-history reads — the controls a non-technical user wants when an AI app is connected to their Slack over MCP.
Windsurf
@sigmashakeinc/rules-windsurf
Official
Verified
Wrangler
@sigmashakeinc/rules-wrangler
Official
Verified
Wrangler is Cloudflare's CLI for deploying Workers, managing D1, KV, R2, and Durable Objects. These rules protect AI agents from destructive remote-database operations, secrets leakage in wrangler.toml, missing compatibility dates, public-bucket misconfiguration, and production deploys without environment gates.
Ai-ml
@sigmashakeinc/rules-ai-ml
Official
Verified
Aider
@sigmashakeinc/rules-aider
Official
Verified
Amp
@sigmashakeinc/rules-amp
Official
Verified
Backend
@sigmashakeinc/rules-backend
Official
Verified
Trust & integrity
Trust center
Engineered for auditors
Signed releases
Every published ruleset is signed with the maintainer's key. The ssg CLI verifies the signature against /api/pubkey before installing.
Content-hash locked
Each version pins a SHA-256 of the indexed rules. Any edit upstream bumps the hash and the version — no silent overrides.
Transparency log
Every publish, update, and resync appends to an append-only Merkle log cross-anchored with sigmashake-compliance.
Open API surface
Browse OpenAPI 3, llms.txt, sitemap.xml, and security.txt. Stable, agent-friendly endpoints.
MCP-native
Connect any agent to mcp.sigmashake.com/sse — six tools cover eval, search, audit, and publish. No SDK required.
Security evidence program
Internal control evidence is collected continuously via sigmashake-compliance with 90-day Object Lock retention. Not a completed SOC 2 attestation.
Contribute a ruleset
Publish rules in one command
Got a ruleset that would protect other teams? Every submitted ruleset is signed, versioned, and auditable. Install ssg, point it at your repo, and it's live on the hub — instantly discoverable by every AI agent host.
~/your-project
$ curl -fsSL https://install.sigmashake.com | sh
$ ssg publish
✓ Parsed 14 rules across 3 technologies
✓ Signed & pushed to hub.sigmashake.com
$ ▍