juanpa1601/stepwise
Claude Code plugin for step-by-step feature delivery: spec, implement, check, audit and close, with ADRs, tests and per-step traceability on every PR.
stack: Python
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
GUARDRAILS
3/5
Blocks destructive commands · No YOLO mode · Sandbox or ask-first rules · details
Quality 20/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit juanpa1601/stepwise/.claude ./rig-stepwise # 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 <redacted> .claude/skills/audit $ npx degit <redacted> .claude/skills/check $ npx degit <redacted> .claude/skills/close $ npx degit <redacted> .claude/skills/implement $ npx degit <redacted> .claude/skills/spec
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"ask": [
"Bash(git push:*)",
"Bash(git commit:*)",
"Bash(gh pr comment:*)",
"Bash(gh pr review:*)",
"Bash(gh pr merge:*)",
"Bash(gh pr edit:*)",
"Bash(gh pr ready:*)",
"Bash(gh api -X *)",
"Bash(gh api * -X *)",
"Bash(gh api * --method *)",
"Bash(gh api * --input *)"
]
}
} Skills (5)
Permissions
deny (0)
—
ask (11)
Bash(git push:*)
Bash(git commit:*)
Bash(gh pr comment:*)
Bash(gh pr review:*)
Bash(gh pr merge:*)
Bash(gh pr edit:*)
Bash(gh pr ready:*)
Bash(gh api -X *)
Bash(gh api * -X *)
Bash(gh api * --method *)
Bash(gh api * --input *)
allow (0)
—
Similar rigs
bitcraft-apps/spec-first
Build faster by writing requirements before code. A Claude Code plugin for spec-driven development
Minimalist 728 tok · · Q0
OleksandrMrn/spec-driven-dev-kit
Spec-driven development kit for AI coding agents: rules, approval gates, skills and templates for Claude Code and Codex
Pragmatist 5.1k tok · · Q41
OleksandrMrn/velspek
Spec-driven development kit for AI coding agents: rules, approval gates, skills and templates for Claude Code and Codex
Pragmatist 5.1k tok · · Q41
adamsaou/overseer
Can a weaker AI catch a stronger one that's hiding something? Black-box audits for hidden objectives in language models: a CLI, a Claude Code plugin and a GitHub Action.
Pragmatist 2.8k tok · · Q0