Slb — AI skill for Claude Code
Two-person rule CLI for AI coding agents: peer review and approval required before running potentially destructive commands.
How to install Slb
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Dicklesworthstone/slb and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Slb does
Two-person rule CLI for AI coding agents: peer review and approval required before running potentially destructive commands.
Alternatives in AI
- Part 4 — Generate AGENTS.md And AI Agent Configuration Files — I'll help you create the instruction files that will guide your AI coding assistant to build your MVP 2.1k ★
- Claude Skills LLM Council — LLM Council — a Claude Code skill that runs your decisions through 5 AI advisors with peer review 1.7k ★
- Paritok 4b V1 — Non-destructive compression gateway for AI coding agents 1.4k ★
README
Simultaneous Launch Button (slb)
[](https://golang.org) [](LICENSE) [](https://github.com/Dicklesworthstone/slb/actions)
A cross-platform CLI that implements a **two-person rule** for running potentially destructive commands from AI coding agents.
When an agent wants to run something risky (e.g., `rm -rf`, `git push --force`, `kubectl delete`, `DROP TABLE`), `slb` requires peer review and explicit approval before execution.
Why This Exists
Coding agents can get tunnel vision, hallucinate, or misunderstand context. A second reviewer (ideally with a different model/tooling) catches mistakes before they become irreversible.
`slb` is built for **multi-agent workflows** where many agent terminals run in parallel and a single bad command could destroy work, data, or infrastructure.
Key Features
- Risk-Based Classification: Commands are automatically classified by risk level
- Client-Side Execution: Commands run in YOUR shell environment (inheriting AWS credentials, kubeconfig, virtualenvs, etc.)
- Command Hash Binding: Approvals bind to the exact command via SHA-256 hash
- SQLite Source of Truth: Project state lives in
.slb/state.db - Agent Mail Integration: Notify reviewers and track audit trails via MCP Agent Mail
- TUI Dashboard: Interactive terminal UI for human reviewers
Risk Tiers
| Tier | Approvals | Auto-approve | Examples |
|---|---|---|---|
| CRITICAL | 2+ | Never | rm -rf /, DROP DATABASE, terraform destroy, git push --force |
| DANGEROUS | 1 | Never | rm -rf ./build, git reset --hard, kubectl delete, DROP TABLE |
| CAUTION | 0 | After 30s | rm file.txt, git branch -d, npm uninstall |
| SAFE | 0 | Immediately | rm *.log, |
Related Skills
Aegis Shellguard
Aegis — the shell guard for AI coding agents. Destructive commands from Claude Code, Codex, or Cursor pause fo
Sudoplz
Give Claude Code, Cursor, and other AI coding agents the ability to run sudo with case-by-case GUI approval. P
Tripline
Guardrails and blame for AI coding agents. Blocks loops, runaway cost and destructive commands in Claude Code
Ensemble
Multi-model consensus debate via the filesystem. LLMs propose, peer-review, rebut, vote and synthesize a group
Gemini Peer Review
Claude Code plugin for AI peer review validation using Google Gemini CLI. Two AI perspectives catch more issue
Peer AI
AI-to-AI peer consultation: install symmetric skills in Claude Code, Codex CLI, and Gemini CLI so any installe
Related Agents
Rule Advisor
Selects optimal rulesets for tasks and performs metacognitive analysis. Use PROACTIVELY before implementation
Board Steward
Use when the GitHub issue tracker needs cleanup: deduping, re-triaging stale issues, honest closes, board-fiel
Human Comment Reader
Comment-reading agent — reads issue/PR threads like a person: maintainer tone, repo culture, implicit rules —
