addit-digital/addit-harness
Config harness for Claude Code — subagents, language conventions, an engineering-loop process, ADRs, and a one-line auto-detecting install
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit addit-digital/addit-harness/agents ./rig-addit-harness/agents $ npx degit addit-digital/addit-harness/skills ./rig-addit-harness/skills $ npx degit addit-digital/addit-harness/hooks ./rig-addit-harness/hooks
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit addit-digital/addit-harness/skills/adr .claude/skills/adr $ npx degit addit-digital/addit-harness/skills/design-conventions .claude/skills/design-conventions $ npx degit addit-digital/addit-harness/skills/dev-flow .claude/skills/dev-flow $ npx degit addit-digital/addit-harness/skills/go-conventions .claude/skills/go-conventions $ npx degit addit-digital/addit-harness/skills/save-plan .claude/skills/save-plan $ npx degit addit-digital/addit-harness/skills/setup .claude/skills/setup $ npx degit addit-digital/addit-harness/skills/telemetry-export .claude/skills/telemetry-export $ npx degit addit-digital/addit-harness/skills/tips .claude/skills/tips
$ curl -fsSL --create-dirs -o .claude/agents/architect-reviewer.md https://raw.githubusercontent.com/addit-digital/addit-harness/main/agents/architect-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/backend-architect.md https://raw.githubusercontent.com/addit-digital/addit-harness/main/agents/backend-architect.md $ curl -fsSL --create-dirs -o .claude/agents/backend-developer.md https://raw.githubusercontent.com/addit-digital/addit-harness/main/agents/backend-developer.md $ curl -fsSL --create-dirs -o .claude/agents/cloud-architect.md https://raw.githubusercontent.com/addit-digital/addit-harness/main/agents/cloud-architect.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/addit-digital/addit-harness/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/addit-digital/addit-harness/main/agents/debugger.md $ curl -fsSL --create-dirs -o .claude/agents/devops-engineer.md https://raw.githubusercontent.com/addit-digital/addit-harness/main/agents/devops-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/figma-designer.md https://raw.githubusercontent.com/addit-digital/addit-harness/main/agents/figma-designer.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-architect.md https://raw.githubusercontent.com/addit-digital/addit-harness/main/agents/frontend-architect.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-developer.md https://raw.githubusercontent.com/addit-digital/addit-harness/main/agents/frontend-developer.md $ curl -fsSL --create-dirs -o .claude/agents/product-owner.md https://raw.githubusercontent.com/addit-digital/addit-harness/main/agents/product-owner.md $ curl -fsSL --create-dirs -o .claude/agents/qa-engineer.md https://raw.githubusercontent.com/addit-digital/addit-harness/main/agents/qa-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/saas-legal-advisor.md https://raw.githubusercontent.com/addit-digital/addit-harness/main/agents/saas-legal-advisor.md $ curl -fsSL --create-dirs -o .claude/agents/task-triager.md https://raw.githubusercontent.com/addit-digital/addit-harness/main/agents/task-triager.md $ curl -fsSL --create-dirs -o .claude/agents/ux-designer.md https://raw.githubusercontent.com/addit-digital/addit-harness/main/agents/ux-designer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (8)
Subagents (15)
| architect-reviewer model: opus | Use this agent when you need to evaluate system design decisions, architectural patterns, and technology choices at the macro level. |
| backend-architect model: opus | Expert backend architect specializing in scalable API design, microservices architecture, and distributed systems. Masters REST/GraphQL/gRPC APIs, event-driven architectures, service mesh patterns, an |
| backend-developer model: sonnet | Use this agent to IMPLEMENT backend features and fixes in code once the design/approach is clear. A senior backend engineer and software craftsman that writes, structures, tests, and verifies code in |
| cloud-architect model: opus | Expert cloud architect specializing in AWS/Azure/GCP/OCI/DigitalOcean multi-cloud infrastructure design, advanced IaC (Terraform/OpenTofu/CDK), FinOps cost optimization, and modern architectural patte |
| code-reviewer model: opus | Use this agent when you need to conduct comprehensive code reviews focusing on code quality, security vulnerabilities, and best practices. |
| debugger model: sonnet | Use this agent when you need to diagnose and fix bugs, identify root causes of failures, or analyze error logs and stack traces to resolve issues. |
| devops-engineer model: sonnet | Use this agent to IMPLEMENT infrastructure automation, CI/CD pipelines, containerization, and deployment workflows once the design/approach is clear. Writes and verifies actual Terraform/OpenTofu, Kub |
| figma-designer model: sonnet | Figma execution agent that creates, edits, and updates design files in Figma via the official Figma MCP server. Materializes UX specs and design-system conventions into Figma frames, components, auto- |
| frontend-architect model: opus | Expert frontend architect specializing in scalable component architecture, rendering strategies, and state management design. Masters React/Next.js application structure, micro-frontend patterns, perf |
| frontend-developer model: sonnet | Use this agent to IMPLEMENT frontend features and fixes in code once the design/approach is clear. A senior frontend engineer and software craftsman that writes, structures, tests, and verifies code i |
| product-owner model: sonnet | Use BEFORE any design to turn a feature, fix, or product request into a clear problem statement — who is affected, current vs desired behavior grounded in the codebase, constraints, non-goals, and tes |
| qa-engineer model: sonnet | Use this agent to VERIFY an implemented feature or fix via e2e and regression testing — writes test scenarios, implements them as executable test code (Playwright, Maestro, or whatever fits the target |
| saas-legal-advisor model: opus | SaaS legal advisor covering international and jurisdiction-specific regulations. Assesses the legal impact of product changes, drafts and reviews privacy policies, terms of service, cookie policies, D |
| task-triager model: sonnet | Use to answer a fixed fact questionnaire about a change request against a repo — which files it would touch, which risk surfaces, what checks exist — so a deterministic script can score it. Reports fa |
| ux-designer model: opus | Expert UX designer specializing in user flows, journey mapping, information architecture, wireframes, and interaction design. Masters usability heuristic evaluation, flow-level accessibility, and UI-p |
Plugins (8)
gopls-lsp@claude-plugins-officialjdtls-lsp@claude-plugins-officialtypescript-lsp@claude-plugins-officialpr-review-toolkit@claude-plugins-officialcommit-commands@claude-plugins-officialsecurity-guidance@claude-plugins-officialfigma@claude-plugins-officialdocument-skills@anthropic-agent-skills
Permissions
deny (0)
—
ask (0)
—
allow (20)
Skill
Read
Grep
Glob
Bash(go test:*)
Bash(go build:*)
Bash(go vet:*)
Bash(gofmt:*)
Bash(mvn test:*)
Bash(mvn verify:*)
Bash(./gradlew test:*)
Bash(./gradlew build:*)
Bash(npm test:*)
Bash(npm run build:*)
Bash(npm run lint:*)
Bash(pnpm test:*)
Bash(pnpm build:*)
Bash(git status)
Bash(git diff:*)
Bash(git log:*)
Similar rigs
dominikbullo/ai-setup
My AI setup — Claude Code skills, agents, and config for engineering work
Orchestrator 749 tok ·
lst97/claude-code-sub-agents
Collection of specialized AI subagents for Claude Code for personal use (full-stack development).
Orchestrator 5.6k tok ·
felipebustillo/dotclaude
A complete reference for configuring Claude Code — agents, skills, rules, hooks, settings, and memory patterns
Orchestrator 300 tok ·
sbstnppl/multi-agent-project-template
A comprehensive template for Python projects with Claude Code integration, featuring a professional multi-agent workflow system for development, testing, documentation, and deployment.
Orchestrator 4.3k tok ·