lantisprime/claude-sdlc
A governance layer for AI-assisted software delivery. Plan, scope, approve, build, test, release — with human sign-off at every gate.
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 lantisprime/claude-sdlc/.claude ./rig-claude-sdlc # 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 lantisprime/claude-sdlc/skills/analyze .claude/skills/analyze $ npx degit lantisprime/claude-sdlc/skills/api-integration .claude/skills/api-integration $ npx degit lantisprime/claude-sdlc/skills/configure .claude/skills/configure $ npx degit lantisprime/claude-sdlc/skills/deploy .claude/skills/deploy $ npx degit lantisprime/claude-sdlc/skills/design .claude/skills/design $ npx degit lantisprime/claude-sdlc/skills/docs .claude/skills/docs $ npx degit lantisprime/claude-sdlc/skills/domain-expert .claude/skills/domain-expert $ npx degit lantisprime/claude-sdlc/skills/gate-signoff .claude/skills/gate-signoff $ npx degit lantisprime/claude-sdlc/skills/help .claude/skills/help $ npx degit lantisprime/claude-sdlc/skills/minimal-code .claude/skills/minimal-code $ npx degit lantisprime/claude-sdlc/skills/plan .claude/skills/plan $ npx degit lantisprime/claude-sdlc/skills/scoping .claude/skills/scoping $ npx degit lantisprime/claude-sdlc/skills/security-review .claude/skills/security-review $ npx degit lantisprime/claude-sdlc/skills/start .claude/skills/start $ npx degit lantisprime/claude-sdlc/skills/status .claude/skills/status $ npx degit lantisprime/claude-sdlc/skills/support .claude/skills/support $ npx degit lantisprime/claude-sdlc/skills/surgical-edit .claude/skills/surgical-edit $ npx degit lantisprime/claude-sdlc/skills/suspend .claude/skills/suspend
$ curl -fsSL --create-dirs -o .claude/agents/maintainer-code-quality-reviewer.md https://raw.githubusercontent.com/lantisprime/claude-sdlc/main/.claude/agents/maintainer-code-quality-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/maintainer-dependency-reviewer.md https://raw.githubusercontent.com/lantisprime/claude-sdlc/main/.claude/agents/maintainer-dependency-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/maintainer-security-reviewer.md https://raw.githubusercontent.com/lantisprime/claude-sdlc/main/.claude/agents/maintainer-security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/maintainer-test-adequacy-reviewer.md https://raw.githubusercontent.com/lantisprime/claude-sdlc/main/.claude/agents/maintainer-test-adequacy-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/rfc-pr-reviewer.md https://raw.githubusercontent.com/lantisprime/claude-sdlc/main/.claude/agents/rfc-pr-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/lantisprime/claude-sdlc/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/observability.md https://raw.githubusercontent.com/lantisprime/claude-sdlc/main/agents/observability.md $ curl -fsSL --create-dirs -o .claude/agents/scope-ingest.md https://raw.githubusercontent.com/lantisprime/claude-sdlc/main/agents/scope-ingest.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/lantisprime/claude-sdlc/main/agents/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/test-designer.md https://raw.githubusercontent.com/lantisprime/claude-sdlc/main/agents/test-designer.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 (18)
analyzeapi-integrationconfiguredeploydesigndocsdomain-expertgate-signoffhelpminimal-codeplanscopingsecurity-reviewstartstatussupportsurgical-editsuspend
Subagents (10)
| maintainer-code-quality-reviewer model: claude-haiku-4-5-20251001 | Use this agent before signing a maintainer Build gate on the sdlc-plugin repo. Reviews the current diff for code-quality concerns: correctness against requirements, readability and naming, anti-overen |
| maintainer-dependency-reviewer model: claude-haiku-4-5-20251001 | Use this agent before signing a maintainer Build gate on the sdlc-plugin repo. Conditionally reviews dependency manifest changes (package.json, requirements.txt, go.mod, Gemfile, pom.xml, Cargo.toml, |
| maintainer-security-reviewer model: claude-haiku-4-5-20251001 | Use this agent before signing a maintainer Build gate on the sdlc-plugin repo. Reviews the current diff for security concerns from the security-review skill checklist (input validation, authN/authZ, s |
| maintainer-test-adequacy-reviewer model: claude-haiku-4-5-20251001 | Use this agent before signing a maintainer Build gate on the sdlc-plugin repo. Reviews the current diff and the touched test files for test-adequacy concerns: coverage of changed lines, missing edge-c |
| rfc-pr-reviewer model: claude-haiku-4-5-20251001 | Use this agent during RFC build-stage (per docs/rfcs/AGENT-RULES.md §3.5) to review a PR diff against an accepted RFC's ## Implementation plan. Verifies plan-conformance: PR files ⊆ plan files, surgic |
| architect | Read-only architecture validator and proposer. Use during Phase 3 Design to validate existing architecture artifacts against the current requirements set, surface deltas, and propose updates — without |
| observability | Produces monitoring, logging, alerting, and runbook artifacts for a deployed change during Phase 7 Support. Writes only into .claude/sdlc/monitoring/ and does not modify application code. |
| scope-ingest | Bounded subagent that turns raw source material (markdown files, plain-text files, pasted text) into a normalized, provenance-traced scope draft at .claude/sdlc/scope-drafts/. Invoked by the plan skil |
| security-reviewer | Read-only security reviewer that audits the current diff against the security-review checklist. Can propose remediations but cannot apply them. Runs parallel to Build and as part of /review. |
| test-designer | Generates test cases from approved requirements during Phase 3 Design. Writes only into .claude/sdlc/test-cases/ and does not touch implementation or existing tests. Every test case traces to one or m |
Hooks (3)
| event | matcher | runs |
|---|---|---|
| Stop | * | ${CLAUDE_PROJECT_DIR}/.claude/hooks/pre-merge-review-gate.sh |
| PostToolUse | Edit|Write|MultiEdit | ${CLAUDE_PROJECT_DIR}/.claude/hooks/rfc-quality-gate.sh |
| PostToolUse | Edit|Write|MultiEdit | ${CLAUDE_PROJECT_DIR}/.claude/hooks/ai-slop-check.sh |
Slash commands (16)
/analyze/build/configure/deploy/design/docs/fix-fast/help/plan/review/start/status/support/suspend/test/token-review
Similar rigs
babushkai/claude-code-config
Production-ready Claude Code configuration defaults. Hooks, Skills, Rules, Permissions, MCP — one-command setup.
Fort Knox 603 tok ·
anujg21/claude-engineering-os
A repository template that gives Claude Code a working engineering method: phased workflow, path-scoped standards, independent review agents, and hooks that block dangerous commands.
Skill Collector 3.1k tok ·
r3dpepper/claude-dotfiles
Claude code workflow harness files. Goes to ~/.claude in user-scoped location.
Fort Knox 1.5k tok ·
cfrs2005/claude-init
Claude Code 中文开发套件 - 为中国开发者定制的零门槛 AI 编程环境。一键安装完整中文化体验，集成 MCP 服务器、智能上下文管理、安全扫描，支持免翻墙访问。让 AI 编程更简单。
Orchestrator 1.5k tok ·