jagdish3135/knit
A multi-agent software team for Claude Code, Codex, Cursor, OpenCode and Antigravity
field: unknown workflow: Frontend & designPlanning & specsTesting & TDDCI/CD & deployPR / code review
stack: JavaScript
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 jagdish3135/knit/.claude ./rig-knit # 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 jagdish3135/knit/.claude/skills/knit-build .claude/skills/knit-build $ curl -fsSL --create-dirs -o .claude/agents/accessibility-tester.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/accessibility-tester.md $ curl -fsSL --create-dirs -o .claude/agents/ai-engineer.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/ai-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/backend-dev.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/backend-dev.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/database-architect.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/database-architect.md $ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/debugger.md $ curl -fsSL --create-dirs -o .claude/agents/devops.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/devops.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-dev.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/frontend-dev.md $ curl -fsSL --create-dirs -o .claude/agents/lean-coder.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/lean-coder.md $ curl -fsSL --create-dirs -o .claude/agents/mobile-developer.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/mobile-developer.md $ curl -fsSL --create-dirs -o .claude/agents/payment-integration.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/payment-integration.md $ curl -fsSL --create-dirs -o .claude/agents/performance-engineer.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/performance-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/product-manager.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/product-manager.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/seo-content-writer.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/seo-content-writer.md $ curl -fsSL --create-dirs -o .claude/agents/tech-writer.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/tech-writer.md $ curl -fsSL --create-dirs -o .claude/agents/tester.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/tester.md $ curl -fsSL --create-dirs -o .claude/agents/ux-designer.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/ux-designer.md $ curl -fsSL --create-dirs -o .claude/agents/ux-researcher.md https://raw.githubusercontent.com/jagdish3135/knit/main/.claude/agents/ux-researcher.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (1)
Subagents (20)
| accessibility-tester model: sonnet | Optional specialist. Accessibility tester. Checks the built UI against WCAG 2.2 AA with automated scans and keyboard and screen-reader walkthroughs. Use for public-facing apps and before release. |
| ai-engineer model: sonnet | Optional specialist. AI/LLM engineer. Builds AI features inside the app (chat, summarizing, extraction, RAG, agents) with prompts, evals, cost limits and safety. Use for [ai] tasks. |
| architect model: opus | Turns the PRD into an architecture, an API contract and a task list, and decides which optional specialists a project needs. Use after the product-manager, or when a feature needs a design decision be |
| backend-dev model: sonnet | Backend developer. Implements the API in openapi.yaml, business logic, authentication and data access. Use for [be] tasks. |
| code-reviewer model: opus | Senior code reviewer. Reviews changes for correctness bugs, contract drift, duplication and performance, and works in a paired loop with the developer until it approves. Use after a build step, in par |
| database-architect model: sonnet | Optional specialist. Database architect. Designs the schema, constraints, indexes and migrations, and tunes slow queries. Use for [db] tasks when the data is complex, large or performance-sensitive. |
| debugger model: opus | Debugger. Finds the root cause of failing tests, crashes and errors before anyone tries a fix. Use when the tester reports failures, or when a bug is reported. |
| devops model: sonnet | DevOps engineer. Sets up repo tooling, environment config, Docker, CI/CD and deployment, and verifies every deploy with a smoke test. Use for [ops] tasks and before shipping. |
| frontend-dev model: sonnet | Frontend developer. Implements the web UI from design.md against the API contract in openapi.yaml. Use for [fe] tasks. |
| lean-coder model: sonnet | Lean coder. Keeps the codebase as small as it can be without losing safety. Checks the plan before building (is each task needed, can existing code, the standard library or the platform do it) and rev |
| mobile-developer model: sonnet | Optional specialist. Mobile developer for iOS and Android apps (React Native with Expo by default, or Flutter). Use for [mobile] tasks. |
| payment-integration model: sonnet | Optional specialist. Payment integration engineer for Stripe or Razorpay: checkout, subscriptions, webhooks and refunds, in test mode. Use for [pay] tasks. |
| performance-engineer model: sonnet | Optional specialist. Performance engineer. Measures page speed, bundle size, API latency, load capacity and slow queries, and reports fixes with numbers. Use for slow pages, heavy traffic, or before a |
| product-manager model: opus | Product manager. Turns the user's idea and the brief into a product requirements doc (PRD) with user stories, acceptance criteria, priorities and out-of-scope. Use first in every Knit build, and whene |
| security-reviewer model: opus | Security reviewer. Writes a threat model at design time and audits code, config and dependencies before release (OWASP Top 10, secrets, auth, injection). Use after the architecture is written, before |
| seo-content-writer model: haiku | Optional specialist. SEO and content writer for marketing sites and landing pages: keywords, page copy, meta tags, structured data, sitemap. Use for [seo] tasks. |
| tech-writer model: haiku | Technical writer. Writes the README, setup and API docs and the changelog from the real code. Use at the end of a build or after any user-facing change. |
| tester model: sonnet | QA / test engineer. Writes and runs unit, API and Playwright end-to-end tests that prove every acceptance criterion, and reports failures. Use after each build step and after every fix. |
| ux-designer model: sonnet | UI/UX designer. Designs user flows, screens, the design system and tokens before frontend work starts, and does a visual check of the built UI against the design. Use for [ux] tasks or when a UI looks |
| ux-researcher model: sonnet | Optional specialist. UX researcher. Builds personas, user journeys, a competitor scan and interview scripts before the PRD and design are written. Use when the users or the problem are not well unders |
Similar rigs
roadhero/claude-code-setup
My actual Claude Code setup: a stack-agnostic engineering spine, auto-activating rule packs, 50 scoped subagents across web/Android/iOS/compute, safety hooks, and a repo scaffolder. From the book "42: The AI Builder's Stack."
Orchestrator 7.3k tok · · Q32
jonase47/ccpr
CCPR is a phase-based project framework for Claude Code
Orchestrator 10.4k tok · · Q14
GinVlad/claude-saas-template
Claude Code template for building SaaS with agentic AI coordination. 5-stage workflow
Orchestrator 612 tok · · Q0
jiaheyi-maggie/claude-code-config
Personal Claude Code configuration — commands, hooks, settings, and global instructions
Orchestrator 7.0k tok · · Q5