By adamrdrew
Drive agent-based development through plan-build-review phases using specialized agents (Scribe, Builder, Overseer) with file-backed state tracking in .ushabti/ for laws, styles, docs, steps, and progress. Enforce invariants, generate structured plans/reviews, and ensure docs stay current with code.
Define code conventions, patterns, and style guide. Use when establishing how things should be built, naming conventions, or architectural preferences.
Implement planned phases step by step. Use when writing code, executing implementation plans, or building features defined by Scribe.
Define project invariants, constraints, and non-negotiable rules. Use when establishing laws, setting boundaries, or capturing what must never change.
Review and approve completed phases. Use when verifying implementation, checking acceptance criteria, or declaring phases complete.
Plan development phases with steps and acceptance criteria. Use when starting new work, breaking down features, or creating implementation plans.
Approve a phase — sets status to complete, marks all steps reviewed, updates linked card. Use when declaring a phase green.
Bootstrap phase context for Builder. Provides current phase, next step, and full phase file contents.
Bootstrap phase context for Overseer. Provides phase under review with full file contents and card metadata.
Verify required Ushabti files exist before proceeding. Use when starting agent work to ensure prerequisites are met.
Mark a card as done by updating its status field to `done` and setting the updated timestamp. This replaces the old ticket archival system where tickets were moved to an `.archived/` directory.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Your development practices have been weighed against Ma’at and found wanting. Come. Let us build.
Ushabti is a lightweight, file-backed, agent-driven development system for Claude Code. It is inspired by spec-kit, but deliberately not tied to spec-driven development. Ushabti is optimized for tight iteration loops, not one-shot bootstrapping.
In ancient Egypt, ushabti were small figurines placed in tombs to do work for you in the afterlife. In this project, Ushabti are small agents that do focused work for you so you can stay at the decision layer.
The road ahead is long. Let us plan accordingly and proceed carefully, for there are many perils along the way. We need not move but one step at a time.
Ushabti exists to account for, control for, and prevent the common failure modes that crop up in AI-augmented engineering. A common criticism you’ll often hear is: “It may be great that you bootstrapped a project so quickly, but wait until you need to extend and maintain your code.” Everybody agrees you can move fast with AI assistance, but there's a great deal of skepticism that working with AI can produce high quality mantainable code.
Ushabti is designed specifically to make maintainable, extensible codebases work with AI-augmented engineering over an indefinitely long time span. The agents and skills are assembled with that primary goal in mind: enable developers working with AI to create software that can be extended and grown indefinitely.
Ushabti sacrifices some of the raw velocity that unstructured AI development provides, but it invests that lost velocity into producing software that stays stable and extensible for as long as the developer wants to keep working.
/plugin marketplace add adamrdrew/marketplace
/plugin install ushabti@adamrdrew
Ushabti skills use read-only bash commands to inspect repository state (e.g., finding the current phase, checking for required files). Following the principle of least privilege, Ushabti grants only the specific commands needed.
Add the following to your project's .claude/settings.json or .claude/settings.local.json:
{
"permissions": {
"allow": [
"Bash([ -f *)",
"Bash([ -d *)",
"Bash(ls *)",
"Bash(grep *)",
"Bash(awk *)",
"Bash(basename *)",
"Bash(echo *)",
"Bash(sed *)",
"Bash(sort *)",
"Bash(tail *)",
"Bash(printf *)"
]
}
}
These permissions grant access to common read-only commands that skills use for file inspection and text processing. If you add new skills that require additional commands, update this list accordingly.
New to Ushabti? Start here:
These guides provide detailed walkthroughs and practical examples. The sections below offer a quick overview.
Development happens in Phases.
A Phase is a bounded unit of work that is:
Once a Phase is green, you move on. No half-finished work. No drifting scope. No invisible state.
Everything is tracked in files inside the repo, not in chat history.
Plan → Build → Review
↑ ↓
└── refine ──┘
There is no implicit “done.” A Phase is done only when the Reviewer marks it green.
The ir-kat skill ("Do the work" in ancient Egyptian) automates the entire Plan → Build → Review cycle. Give it a PHASE_PROMPT and it orchestrates Scribe, Builder, and Overseer end-to-end, including retry loops if the Overseer kicks back (up to 3 attempts before declaring the phase blocked).
/ir-kat Build a REST API for user management with JWT authentication
Or pass a file:
/ir-kat /path/to/PHASE_PROMPT.md
Ir-kat is also the orchestration layer used by Pharaoh, the autonomous phase runner.
Ushabti separates what must never change from what evolves.
(.ushabti/laws.md)
Project invariants that must always hold.
npx claudepluginhub adamrdrew/marketplace --plugin ushabtiA Model Context Protocol (MCP) server that provides LLM access to macOS AppleScript automation.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.