agentrigs
+ submit rig
~ / rigs / BaseInfinity / claude-sdlc-harness

BaseInfinity/claude-sdlc-harness

Self-evolving SDLC enforcement for AI coding agents — hooks, skills, and one-command setup for Claude Code. Plan before coding, test before shipping, escalate when uncertain. Measures itself getting better over time.

↗ GitHub ★ 50 no license updated 5d ago personal setup Claude CodeCodex Claude plugin
share on X
ARCHETYPE
Automator
Hooks on every lifecycle event: format, lint, notify, log.
CONTEXT TAX · EVERY TURN
~3.1k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
3/5
Blocks destructive commands · Pre-tool screening hook · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit BaseInfinity/claude-sdlc-harness/.claude ./rig-claude-sdlc-harness  # 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 BaseInfinity/claude-sdlc-harness/cowork/skills/feedback .claude/skills/feedback
$ npx degit BaseInfinity/claude-sdlc-harness/cowork/skills/sdlc .claude/skills/sdlc
$ npx degit BaseInfinity/claude-sdlc-harness/skills/setup .claude/skills/setup
$ npx degit BaseInfinity/claude-sdlc-harness/skills/update .claude/skills/update

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Write|Edit|MultiEdit",
        "hooks": [
          {
            "type": "command",
            "command": "SDLC_TDD_SRC_PATTERN='hooks/|cli/|.github/workflows/' \"$CLAUDE_PROJECT_DIR\"/hooks/tdd-pretool-check.sh"
          }
        ]
      },
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "\"$CLAUDE_PROJECT_DIR\"/hooks/codex-gate-check.sh"
          },
          {
            "type": "command",
            "command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/merge-gate-check.sh"
          }
        ]
      }
    ]
  }
}

Skills (4)

feedbacksdlcclaude-setup-wizardclaude-update-wizard

Hooks (9)

eventmatcherruns
UserPromptSubmit*"$CLAUDE_PROJECT_DIR"/hooks/sdlc-prompt-check.sh
PreToolUseWrite|Edit|MultiEditSDLC_TDD_SRC_PATTERN='hooks/|cli/|.github/workflows/' "$CLAUDE_PROJECT_DIR"/hooks/tdd-pretool-check.sh
PreToolUseBash"$CLAUDE_PROJECT_DIR"/hooks/codex-gate-check.sh
PreToolUseBash"$CLAUDE_PROJECT_DIR"/.claude/hooks/merge-gate-check.sh
InstructionsLoaded*"$CLAUDE_PROJECT_DIR"/hooks/instructions-loaded-check.sh
SessionStart*"$CLAUDE_PROJECT_DIR"/hooks/model-effort-check.sh
SessionStart*"$CLAUDE_PROJECT_DIR"/hooks/token-spike-check.sh
PreCompactmanual"$CLAUDE_PROJECT_DIR"/hooks/precompact-seam-check.sh
Stop*"$CLAUDE_PROJECT_DIR"/hooks/codex-review-stop-check.sh

Permissions

deny (0)
—
ask (0)
—
allow (42)
mcp__playwright__browser_take_screenshot
mcp__playwright__browser_snapshot
mcp__playwright__browser_console_messages
mcp__playwright__browser_network_requests
Bash(./tests/test-hooks.sh *)
Bash(./tests/test-evaluate-bugs.sh *)
Bash(./tests/test-api-feature-detection.sh *)
Bash(npm ls *)
Bash(./tests/test-doc-consistency.sh *)
Bash(./tests/test-cowork-drift.sh *)
Bash(./tests/test-merge-gate.sh *)
Bash(./tests/test-cross-model-clearance.sh *)
Bash(./tests/test-audit-session-load.sh *)
Bash(./tests/test-roadmap-integrity.sh *)
Bash(./tests/test-workflow-triggers.sh *)
Bash(./tests/test-plugin.sh *)
Bash(./tests/test-self-update.sh *)
Bash(./tests/test-cli.sh *)
Bash(./tests/test-release-drift.sh *)
Bash(npm view *)
Bash(./tests/test-codex-gate-command-position.sh *)
Bash(./tests/test-run-review-leg.sh *)
Bash(./tests/test-review-verdict-schema.sh *)
Bash(./tests/test-hook-stdin-bounded.sh *)
Bash(./tests/test-review-leg-launcher-required.sh *)
Bash(shellcheck *)
Bash(./scripts/post-comment.sh *)
Bash(./tests/test-escalation-ladder.sh *)
Bash(./tests/test-docs-usability.sh *)
Bash(gh search issues *)
Bash(gh search repos *)
Bash(npm whoami *)
mcp__claude-in-chrome__find
mcp__claude-in-chrome__navigate
mcp__claude-in-chrome__tabs_context_mcp
mcp__claude-in-chrome__tabs_create_mcp
mcp__claude-in-chrome__read_page
mcp__claude-in-chrome__get_page_text
mcp__claude-in-chrome__read_console_messages
mcp__claude-in-chrome__read_network_requests
mcp__claude-in-chrome__computer
mcp__claude-in-chrome__browser_batch

Similar rigs

grandheman/claude-sdlc
AI-Native Software Development Lifecycle for Claude Code — 15 role-based skills covering every SDLC phase, from project kickoff to production monitoring. Works with superpowers plugin, OpenRouter council, and Playwright MCP.
★ 1 project Claude Code 3 skills 1mo ago
Minimalist 105 tok ·
lool-ventures/founder-skills
AI agent skills for high-velocity startup founders
★ 42 collection Claude Code 7 skills 4d ago
Pragmatist 39.9k tok ·
thehimanshushukla/personal-cortex
Cortex: a working record for your AI sessions. Guided setup, start card, enforced logging, follow-ups, and Suggest. Plugin for Claude Code and Codex; its AGENTS.md also works in Cursor, Gemini CLI and Copilot.
★ 1 project Claude CodeCodexGemini CLI 14 skills 3d ago
Skill Collector 2.3k tok ·
Freakling/SaaSAllTheThings
Build a B2B SaaS from scratch, or turn a working proof of concept or existing app into a mature, multi-tenant SaaS on Azure, with an AI assistant: you own the product, the framework owns and enforces the architecture (event-driven Azure Fun
★ 0 project Claude CodeCodex 18 skills 2 agents 3 hooks today
Fort Knox 3.9k tok ·
copied ✓