felipefontoura/spec-driven-development-book
The definitive guide to Spec-Driven Development: build software with AI agents, from method to production code. Book in EN + pt-BR with a ready-to-use SDD kit for Claude Code.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit felipefontoura/spec-driven-development-book/sdd-kit/.claude ./rig-spec-driven-development-book # 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 felipefontoura/spec-driven-development-book/sdd-kit/.claude/skills/sdd-exec .claude/skills/sdd-exec $ npx degit felipefontoura/spec-driven-development-book/sdd-kit/.claude/skills/sdd-idea .claude/skills/sdd-idea $ npx degit felipefontoura/spec-driven-development-book/sdd-kit/.claude/skills/sdd-init .claude/skills/sdd-init $ npx degit felipefontoura/spec-driven-development-book/sdd-kit/.claude/skills/sdd-plan .claude/skills/sdd-plan $ npx degit felipefontoura/spec-driven-development-book/sdd-kit/.claude/skills/sdd-prd .claude/skills/sdd-prd $ npx degit felipefontoura/spec-driven-development-book/sdd-kit/.claude/skills/sdd-review .claude/skills/sdd-review $ npx degit felipefontoura/spec-driven-development-book/sdd-kit/.claude/skills/sdd-spec .claude/skills/sdd-spec $ npx degit felipefontoura/spec-driven-development-book/sdd-kit/.claude/skills/sdd-status .claude/skills/sdd-status $ npx degit felipefontoura/spec-driven-development-book/sdd-kit/.claude/skills/sdd-steering .claude/skills/sdd-steering $ npx degit felipefontoura/spec-driven-development-book/sdd-kit/.claude/skills/sdd-tasks .claude/skills/sdd-tasks
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/felipefontoura/spec-driven-development-book/main/sdd-kit/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/felipefontoura/spec-driven-development-book/main/sdd-kit/.claude/agents/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/felipefontoura/spec-driven-development-book/main/sdd-kit/.claude/agents/reviewer.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 (10)
Subagents (3)
| architect model: inherit | Produces requirements.md and design.md from an approved idea or feature request. Use for the WHAT and the HOW — user stories, EARS requirements, data models, API contracts, technical decisions with ra |
| implementer model: inherit | Implements one approved task from tasks.md — code plus tests — after checking that .status reads tasks:approved. Follows the spec exactly, stops on ambiguity instead of guessing, and reports verificat |
| reviewer model: inherit | Reviews an implementation against requirements.md, design.md, tasks.md, and the produced code in a fresh context. Reports coverage gaps and spec violations with verification evidence — not stylistic o |
Similar rigs
felipefontoura/pi-sdd-kit
Spec-Driven Development skill pack for the Pi coding agent: steering docs, .status gates, EARS, and a PRD→SPEC→TASKS→EXEC→REVIEW pipeline.
Skill Collector 3.0k tok · · Q0
yuroka-studio/nightshift-agents
Scheduled Claude Code agents that take one task from a backlog, open a PR with real test evidence, and never merge or deploy on their own.
Fort Knox 1.0k tok · · Q61
Trolzie/claude-loop-systems-demo
A small demo of Markdown-as-system AI dev loops with Claude Code: issues → agents → skills → verification.
Pragmatist 480 tok · · Q15
homeofe/improvements
Portable, LLM-agnostic framework for multi-model AI workflows: model routing, structured agent handoff (AAHP), and a phased agent pipeline. MIT.
Orchestrator 1.4k tok · · Q24