Claude commands

Bootstrap Checkov on a developer laptop, run static or plan-level Terraform security scanning for AWS/Azure/GCP/EKS, resolve private GitHub modules via gh CLI, generate pre-commit hooks, produce multi-format output (cli/json/sarif/junit), and fix violations with AI-generated patches. Use when asked to "scan my Terraform", "run checkov", "check my IaC for security issues", "set up checkov pre-commit", or "fix checkov findings".

Design, run, and debug Chaos Engineering experiments on Kubernetes using Litmus Chaos v3 and Chaos Mesh v2. Covers fault injection (pod-delete, network-loss, CPU stress, node-drain), steady-state hypothesis probes, GameDay runbooks, scheduled experiments, DORA feedback loop, and RBAC setup. Use when asked to "inject a pod fault", "run a GameDay", "schedule chaos experiments", or "debug why my ChaosEngine is stuck".

Azure identity (Workload Identity, OIDC, Entra ID), resource tagging, AKS platform patterns, RBAC scoping, and production-readiness review — with Terraform generation.

Structured guidance for AWS CloudFront distributions, WAF web ACLs, Lambda@Edge, CloudFront Functions, Firewall Manager multi-account enforcement, and IAM/IRSA patterns. Covers OAC, cache policies, security headers, managed rule groups, rate limiting, FMS FIRST/MIDDLE/LAST ownership model, and production-ready Terraform generation.

AWS profile management for MCP servers — discover profiles across SSO, Granted, and assumed-role chains, check credential TTL, switch profiles across VS Code and Claude Code MCP configs, and scan AWS Organization accounts.

Generate, convert, and maintain animated GitHub-safe Markdown documents with animated SVG diagrams. Covers four SVG patterns (architecture flow, lifecycle loop, field carousel, timeline phases), guided interview for any doc type (README, architecture guide, runbook, API reference, tutorial, RFC, post-mortem, how-it-works, or custom), converting existing plain Markdown, diffing for stale diagrams, quality auditing, local preview, and multi-platform export. Use when asked to "create a README for X", "write an architecture doc", "animate this guide", "convert my doc to animated", "check if my diagrams are stale", or "export my doc for Confluence".

Diagnose trust. Process gap, or they stopped trusting you.

Find the receipt. A dated line, or it did not happen.

Prepare the meeting. One page from the record.

Promised, measured, accepted. A number nobody signed is claimed, not delivered.

They operate it without you.

This directory contains the command implementations for the fast-agent CLI.

Check for or install a verified Tree Ring Memory CLI update without changing installation scope

Decompose a large feature into multiple dependency-aware specs (epic triage)

Generate implementation tasks from design

Switch active spec

Show all specs and their current status

Smart entry point that detects if you need a new spec or should resume existing

Run or re-run research phase for current spec

Generate requirements from goal and research

Update spec files methodically after execution (requirements -> design -> tasks)

Run or resume an optional prototype

Create new spec and start research phase

Index codebase components and external resources into searchable specs