lhpaul/ai-dev-framework-template
A tool-agnostic AI-assisted development framework template. Structured workflow (Spec → Plan → Implement → Review) with canonical protocols, agent definitions for Claude Code/Cursor, and a guided project setup.
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 lhpaul/ai-dev-framework-template/.claude ./rig-ai-dev-framework-template # inspect, then merge into .claude/ 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 lhpaul/ai-dev-framework-template/.agents/skills/add-backlog-item .claude/skills/add-backlog-item $ npx degit lhpaul/ai-dev-framework-template/.agents/skills/code-review .claude/skills/code-review $ npx degit lhpaul/ai-dev-framework-template/.agents/skills/graduate-development .claude/skills/graduate-development $ npx degit lhpaul/ai-dev-framework-template/.agents/skills/merged-qa-tester .claude/skills/merged-qa-tester $ npx degit lhpaul/ai-dev-framework-template/.agents/skills/post-merge-qa .claude/skills/post-merge-qa $ npx degit lhpaul/ai-dev-framework-template/.agents/skills/prepare-release .claude/skills/prepare-release $ npx degit lhpaul/ai-dev-framework-template/.agents/skills/retrospective .claude/skills/retrospective $ npx degit lhpaul/ai-dev-framework-template/.agents/skills/run-epic .claude/skills/run-epic $ npx degit lhpaul/ai-dev-framework-template/.agents/skills/run-item-work .claude/skills/run-item-work $ npx degit lhpaul/ai-dev-framework-template/.agents/skills/run-item .claude/skills/run-item $ npx degit lhpaul/ai-dev-framework-template/.agents/skills/run-items .claude/skills/run-items $ npx degit lhpaul/ai-dev-framework-template/.agents/skills/run-reviewer-loop .claude/skills/run-reviewer-loop $ npx degit lhpaul/ai-dev-framework-template/.agents/skills/run-work .claude/skills/run-work $ npx degit lhpaul/ai-dev-framework-template/.agents/skills/sync-template .claude/skills/sync-template $ npx degit lhpaul/ai-dev-framework-template/.codex/skills/batch-merge .claude/skills/batch-merge $ npx degit lhpaul/ai-dev-framework-template/.codex/skills/post-merge-cleanup .claude/skills/post-merge-cleanup $ npx degit lhpaul/ai-dev-framework-template/.codex/skills/workflow-code-reviewer .claude/skills/workflow-code-reviewer $ npx degit lhpaul/ai-dev-framework-template/.codex/skills/workflow-implementer .claude/skills/workflow-implementer $ npx degit lhpaul/ai-dev-framework-template/.codex/skills/workflow-item-orchestrator .claude/skills/workflow-item-orchestrator $ npx degit lhpaul/ai-dev-framework-template/.codex/skills/workflow-orchestrator .claude/skills/workflow-orchestrator $ npx degit lhpaul/ai-dev-framework-template/.codex/skills/workflow-plan-reviewer .claude/skills/workflow-plan-reviewer $ npx degit lhpaul/ai-dev-framework-template/.codex/skills/workflow-plan-writer .claude/skills/workflow-plan-writer $ npx degit lhpaul/ai-dev-framework-template/.codex/skills/workflow-project-setup .claude/skills/workflow-project-setup $ npx degit lhpaul/ai-dev-framework-template/.codex/skills/workflow-retrospective .claude/skills/workflow-retrospective $ npx degit lhpaul/ai-dev-framework-template/.codex/skills/workflow-reviewer-loop .claude/skills/workflow-reviewer-loop $ npx degit lhpaul/ai-dev-framework-template/.codex/skills/workflow-spec-reviewer .claude/skills/workflow-spec-reviewer $ npx degit lhpaul/ai-dev-framework-template/.codex/skills/workflow-spec-writer .claude/skills/workflow-spec-writer $ npx degit lhpaul/ai-dev-framework-template/.codex/skills/workflow-sync-template .claude/skills/workflow-sync-template
$ curl -fsSL --create-dirs -o .claude/agents/automated-reviewer-loop.md https://raw.githubusercontent.com/lhpaul/ai-dev-framework-template/main/.claude/agents/automated-reviewer-loop.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/lhpaul/ai-dev-framework-template/main/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/design-reviewer.md https://raw.githubusercontent.com/lhpaul/ai-dev-framework-template/main/.claude/agents/design-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/developer.md https://raw.githubusercontent.com/lhpaul/ai-dev-framework-template/main/.claude/agents/developer.md $ curl -fsSL --create-dirs -o .claude/agents/implementation-plan-reviewer.md https://raw.githubusercontent.com/lhpaul/ai-dev-framework-template/main/.claude/agents/implementation-plan-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/item-orchestrator.md https://raw.githubusercontent.com/lhpaul/ai-dev-framework-template/main/.claude/agents/item-orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/orchestrator.md https://raw.githubusercontent.com/lhpaul/ai-dev-framework-template/main/.claude/agents/orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/post-merge-qa.md https://raw.githubusercontent.com/lhpaul/ai-dev-framework-template/main/.claude/agents/post-merge-qa.md $ curl -fsSL --create-dirs -o .claude/agents/product-manager.md https://raw.githubusercontent.com/lhpaul/ai-dev-framework-template/main/.claude/agents/product-manager.md $ curl -fsSL --create-dirs -o .claude/agents/project-setup.md https://raw.githubusercontent.com/lhpaul/ai-dev-framework-template/main/.claude/agents/project-setup.md $ curl -fsSL --create-dirs -o .claude/agents/retrospective.md https://raw.githubusercontent.com/lhpaul/ai-dev-framework-template/main/.claude/agents/retrospective.md $ curl -fsSL --create-dirs -o .claude/agents/smoke-tester.md https://raw.githubusercontent.com/lhpaul/ai-dev-framework-template/main/.claude/agents/smoke-tester.md $ curl -fsSL --create-dirs -o .claude/agents/spec-reviewer.md https://raw.githubusercontent.com/lhpaul/ai-dev-framework-template/main/.claude/agents/spec-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/tech-lead.md https://raw.githubusercontent.com/lhpaul/ai-dev-framework-template/main/.claude/agents/tech-lead.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 (28)
add-backlog-itemcode-reviewgraduate-developmentmerged-qa-testerpost-merge-qaprepare-releaseretrospectiverun-epicrun-item-workrun-itemrun-itemsrun-reviewer-looprun-worksync-templatebatch-mergepost-merge-cleanupworkflow-code-reviewerworkflow-implementerworkflow-item-orchestratorworkflow-orchestratorworkflow-plan-reviewerworkflow-plan-writerworkflow-project-setupworkflow-retrospectiveworkflow-reviewer-loopworkflow-spec-reviewerworkflow-spec-writerworkflow-sync-template
Subagents (14)
| automated-reviewer-loop model: haiku | Run the automated reviewer loop (and CI loop) for a PR. Use when the user wants to run the reviewer loop on a specific PR or the current branch's PR until it is ready for human review or escalated. |
| code-reviewer model: sonnet | Development review stage. Use when an implementation PR needs review against the spec, plan, and best practices. Applies fixes directly for blocking and important issues. Reports issues requiring huma |
| design-reviewer model: opus | Design review stage. Use when an implementation PR includes frontend file changes. Launches a browser via the configured browser_automation.provider, renders affected pages or components, captures scr |
| developer model: opus | In Development stage. Handles four paths — Full Pipeline (feature with spec+plan), Refactor (code restructuring with plan only, no spec), Fast Track (bug or simple change, no spec/plan needed), and Ho |
| implementation-plan-reviewer model: opus | Plan review stage. Use when an implementation plan branch or PR needs review for spec alignment, completeness, and feasibility. Reads the spec, plan, and codebase to validate the approach, and can pus |
| item-orchestrator model: opus | Coordination agent for a single workflow item via /run-item (or deprecated /run-item-work). Runs the shared bounded prelude then Protocol 91 until waiting on a human, blocked, or escalated. |
| orchestrator model: haiku | Batch orchestration agent. Discovers what can advance or start, proposes the largest safe batch by priority and parallelization feasibility, dispatches approved item work, and supervises the batch unt |
| post-merge-qa model: opus | Post-merge QA on develop or develop-<slug>. Confirmed scope, environment preflight, flow/UX exercise, optional design-asset fidelity, one fix PR for safe defects (no backlog item). |
| product-manager model: opus | Spec Ready stage. Use when a new feature needs a spec written. Conducts a structured alignment conversation with the human, then writes the feature spec, runs its reviewer gate, and resolves PR readin |
| project-setup model: sonnet | Onboarding agent. Run this when first setting up a new project from this template. Guides a structured conversation to generate all project-specific documentation (business domain, architecture, tech |
| retrospective model: sonnet | Retrospective analysis agent. Analyzes completed work (a batch or individual item) to identify process improvement opportunities, presents them to the human, and executes the chosen action for each. U |
| smoke-tester model: opus | Smoke test stage. Use when a code review has been approved and the implementation needs manual smoke testing before merge. Executes the smoke test runbook using browser automation. |
| spec-reviewer model: opus | Spec review stage. Use when a spec branch or PR needs review for completeness, clarity, and testability. Applies fixes directly where possible, can push reviewer-loop fixes, and reports issues requiri |
| tech-lead model: opus | Plan Ready stage. Use when an implementation plan needs to be written. For Full Pipeline items, a spec must be approved first. For Refactor items, the work item brief replaces the spec. Reads the code |
Slash commands (16)
/add-backlog-item/batch-merge/code-review/graduate-development/merged-qa-tester/post-merge-cleanup/post-merge-qa/prepare-release/retrospective/run-epic/run-item-work/run-item/run-items/run-reviewer-loop/run-work/sync-template
Cursor rules (3)
codedocumentationworkflow
Permissions
deny (0)
—
ask (0)
—
allow (19)
Bash(gh issue:*)
Bash(gh pr:*)
Bash(git add:*)
Bash(git branch:*)
Bash(git checkout:*)
Bash(git commit:*)
Bash(git diff:*)
Bash(git fetch:*)
Bash(git log:*)
Bash(git pull:*)
Bash(git push:*)
Bash(git stash:*)
Bash(git status:*)
Bash(pnpm:*)
Edit(.claude/agents/**)
Write(.claude/agents/**)
Edit(.cursor/agents/**)
Write(.cursor/agents/**)
WebFetch(domain:github.com)
Similar rigs
ThinhHoang1/claude-code-agent-team
An AI dev team for Claude Code agent teams: 8 role agents, a HANDOFF protocol and 3 hook quality gates — with the TeammateIdle infinite-loop bug fixed and regression-tested.
Orchestrator 1.6k tok ·
giuliano-aparecido/agent-config
Fleet-wide, tool-agnostic conventions for AI coding assistants, shared as a git submodule. Experimental project exploring agentic coding workflows with Claude Code.
Minimalist 1.4k tok ·
caotrongtin99/nextjs-nestjs-claude-code-setup
Next.js setup with Claude AI integration for automated code generation, review, and optimization workflow
Pragmatist 91 tok ·
ameya-vichare/claude-sdd-starter
A platform-agnostic Claude Code setup for engineering teams, using an interactive setup wizard that tailors everything to your project and provides a spec-driven feature development workflow.
Orchestrator 2.3k tok ·