redhoram/claude-pipeline-template
Reusable Claude Code agent framework for complex CRUD apps — /ship pipeline: planner, designer, coder, tester, reviewer.
stack: Python
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 redhoram/claude-pipeline-template/.claude ./rig-claude-pipeline-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 redhoram/claude-pipeline-template/.claude/skills/antislop-code .claude/skills/antislop-code $ npx degit redhoram/claude-pipeline-template/.claude/skills/antislop-human .claude/skills/antislop-human $ npx degit redhoram/claude-pipeline-template/.claude/skills/antislop-layoutmobile .claude/skills/antislop-layoutmobile $ npx degit redhoram/claude-pipeline-template/.claude/skills/antislop-ui .claude/skills/antislop-ui $ npx degit redhoram/claude-pipeline-template/.claude/skills/antislop .claude/skills/antislop $ npx degit redhoram/claude-pipeline-template/.claude/skills/api-contract-guardian .claude/skills/api-contract-guardian $ npx degit redhoram/claude-pipeline-template/.claude/skills/architecture-clean-code .claude/skills/architecture-clean-code $ npx degit redhoram/claude-pipeline-template/.claude/skills/humanizer .claude/skills/humanizer $ npx degit redhoram/claude-pipeline-template/.claude/skills/performance-profiler .claude/skills/performance-profiler $ npx degit redhoram/claude-pipeline-template/.claude/skills/premium-design .claude/skills/premium-design $ npx degit redhoram/claude-pipeline-template/.claude/skills/relational-mastery .claude/skills/relational-mastery $ npx degit redhoram/claude-pipeline-template/.claude/skills/secure-coding .claude/skills/secure-coding $ npx degit redhoram/claude-pipeline-template/.claude/skills/systematic-debugging .claude/skills/systematic-debugging $ npx degit redhoram/claude-pipeline-template/.claude/skills/testing-discipline .claude/skills/testing-discipline $ npx degit redhoram/claude-pipeline-template/.claude/skills/ux-research .claude/skills/ux-research
$ curl -fsSL --create-dirs -o .claude/agents/coder.md https://raw.githubusercontent.com/redhoram/claude-pipeline-template/main/.claude/agents/coder.md $ curl -fsSL --create-dirs -o .claude/agents/deployer.md https://raw.githubusercontent.com/redhoram/claude-pipeline-template/main/.claude/agents/deployer.md $ curl -fsSL --create-dirs -o .claude/agents/drafter.md https://raw.githubusercontent.com/redhoram/claude-pipeline-template/main/.claude/agents/drafter.md $ curl -fsSL --create-dirs -o .claude/agents/gatekeeper.md https://raw.githubusercontent.com/redhoram/claude-pipeline-template/main/.claude/agents/gatekeeper.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/redhoram/claude-pipeline-template/main/.claude/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/tester.md https://raw.githubusercontent.com/redhoram/claude-pipeline-template/main/.claude/agents/tester.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 (15)
antislop-codeantislop-humanantislop-layoutmobileantislop-uiantislopapi-contract-guardianarchitecture-clean-codehumanizerperformance-profilerpremium-designrelational-masterysecure-codingsystematic-debuggingtesting-disciplineux-research
Subagents (6)
| coder model: sonnet | Writes code based on the spec produced by the Planner. Use once spec.md exists in the .pipeline/ folder. |
| deployer model: sonnet | Prepares a SHIP-verdict change for production deployment. Use as the last step of /ship, only after the gatekeeper's verdict is SHIP. |
| drafter model: opus | Drafts the UI/UX spec (screens, flows, components, states, visual direction) from the technical spec before coding. Use for features with a UI surface, pages, components, or user-facing flows. Skip fo |
| gatekeeper model: opus | Gives the final verdict (SHIP, NEEDS WORK, or BLOCK) based on the Coder's and Tester's output. Use as the last step of the /ship or /fix pipeline. |
| planner model: opus | Turns a feature request into a technical spec before coding starts. Use when the user requests a new feature via /ship. |
| tester model: sonnet | Runs and checks the code written by the Coder. Use once changelog.md exists in the .pipeline/ folder. |
Slash commands (2)
/fix/ship
Similar rigs
miqdadbadjuber/anti-slop
Rules for an AI coding agent to filter out generic AI-generated UI designs, text, and code.
Pragmatist 258 tok · · Q0
xazaj/sdlc-playbook
Decision playbooks for coding agents — 给 coding agent 的开发全链路决策手册。每个 SDLC 阶段一份选型矩阵:该装什么、用哪套设计系统、走 SDD 还是 TDD。
Pragmatist 1.5k tok · · Q0
redhoram/claude-landing-template
Reusable Claude Code agent framework for landing pages & simple apps — visual-loop /craft + /polish: designer, builder, qa.
Orchestrator 4.8k tok · · Q10
BillDX/spicy-to-dark-factory-starter
Workshop starter for 'From Spicy Autocomplete to Dark Factory: Agentic Coding in Practice' — a FastAPI mini-app with a full Claude Code harness (agents, slash commands, hooks, sandbox settings) and self-paced exercises.
Orchestrator 706 tok · · Q18