johanolofsson72/Claude
Drop-in Claude Code configuration for .NET/fullstack projects: deterministic hooks, a spec-driven pipeline, subagents, skills, and formal verification with Allium and TLA+
ARCHETYPE
YOLO Cowboy
Permissions? Never heard of 'em. Ships at the speed of `--dangerously-skip-permissions`.
GUARDRAILS
2/5
Blocks destructive commands · Pre-tool screening hook · details
Quality 67/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit johanolofsson72/Claude/.claude ./rig-claude # 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 johanolofsson72/Claude/.claude/skills/allium .claude/skills/allium $ npx degit johanolofsson72/Claude/.claude/skills/code-review .claude/skills/code-review $ npx degit johanolofsson72/Claude/.claude/skills/deploy-checklist .claude/skills/deploy-checklist $ npx degit johanolofsson72/Claude/.claude/skills/explore-codebase .claude/skills/explore-codebase $ npx degit johanolofsson72/Claude/.claude/skills/lane-status .claude/skills/lane-status $ npx degit johanolofsson72/Claude/.claude/skills/project-update .claude/skills/project-update $ npx degit johanolofsson72/Claude/.claude/skills/project-wizard .claude/skills/project-wizard $ npx degit johanolofsson72/Claude/.claude/skills/sync-template .claude/skills/sync-template $ npx degit johanolofsson72/Claude/.claude/skills/tla .claude/skills/tla $ npx degit johanolofsson72/Claude/.claude/skills/ui-ux-pro-max .claude/skills/ui-ux-pro-max $ npx degit johanolofsson72/Claude/.claude/skills/update-template .claude/skills/update-template
$ curl -fsSL --create-dirs -o .claude/agents/db-agent.md https://raw.githubusercontent.com/johanolofsson72/Claude/main/.claude/agents/db-agent.md $ curl -fsSL --create-dirs -o .claude/agents/dotnet-reviewer.md https://raw.githubusercontent.com/johanolofsson72/Claude/main/.claude/agents/dotnet-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/security-scanner.md https://raw.githubusercontent.com/johanolofsson72/Claude/main/.claude/agents/security-scanner.md $ curl -fsSL --create-dirs -o .claude/agents/test-runner.md https://raw.githubusercontent.com/johanolofsson72/Claude/main/.claude/agents/test-runner.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Bash(rm -rf *)",
"Bash(rm -fr *)",
"Bash(sudo *)",
"Bash(git push --force*)",
"Bash(git push *--force*)",
"Bash(git reset --hard*)",
"Bash(git clean -f*)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Read|Edit|Write|MultiEdit|NotebookEdit|Grep|Glob|Bash",
"hooks": [
{
"type": "command",
"command": "bash \"$CLAUDE_PROJECT_DIR/scripts/sensitive-file-guard-hook.sh\""
}
]
},
{
"matcher": "Edit|Write|MultiEdit|NotebookEdit|Bash|AskUserQuestion|mcp__.*",
"hooks": [
{
"type": "command",
"command": "bash \"$CLAUDE_PROJECT_DIR/scripts/trust-anchor-guard-hook.sh\""
}
]
},
{
"matcher": "Edit|Write|MultiEdit|NotebookEdit|Bash|mcp__.*",
"hooks": [
{
"type": "command",
"command": "bash \"$CLAUDE_PROJECT_DIR/scripts/settings-edit-guard-hook.sh\""
}
]
},
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "[ -f graphify-out/graph.json ] || { cat >/dev/null; exit 0; }; CMD=$(python3 -c \"import json,sys; d=json.load(sys.stdin); print(d.get('tool_input',d).get('command',''))\" 2>/dev/null || true); case \"$CMD\" in *grep*|*rg\\ *|*ripgrep*|*find\\ *|"
},
{
"type": "command",
"command": "bash \"$CLAUDE_PROJECT_DIR/scripts/bash-write-guard-hook.sh\""
},
{
"type": "command",
"command": "bash \"$CLAUDE_PROJECT_DIR/scripts/destructive-command-guard-hook.sh\""
},
{
"type": "command",
"command": "bash \"$CLAUDE_PROJECT_DIR/scripts/stryker-guard-hook.sh\""
}
]
},
{
"matcher": "Edit|Write|MultiEdit|NotebookEdit",
"hooks": [
{
"type": "command",
"command": "bash \"$CLAUDE_PROJECT_DIR/scripts/spec-register-guard-hook.sh\""
},
{
"type": "command",
"command": "bash \"$CLAUDE_PROJECT_DIR/scripts/pipeline-state-guard-hook.sh\""
},
{
"type": "command",
"command": "bash \"$CLAUDE_PROJECT_DIR/scripts/spec-interview-guard-hook.sh\""
},
{
"type": "command",
"command": "bash \"$CLAUDE_PROJECT_DIR/scripts/core-machinery-guard-hook.sh\""
},
{
"type": "command",
"command": "bash \"$CLAUDE_PROJECT_DIR/scripts/core-owed-tick-guard-hook.sh\""
}
]
},
{
"matcher": "Edit|Write",
"hooks": [
{
"type": "command",
"command": "bash \"$CLAUDE_PROJECT_DIR/scripts/ui-design-hook.sh\""
},
{
"type": "command",
"command": "bash \"$CLAUDE_PROJECT_DIR/scripts/sqlite-nfs-safety-hook.sh\""
}
]
}
]
}
} Skills (11)
alliumcode-reviewdeploy-checklistexplore-codebaselane-statusproject-updateproject-wizardsync-templatetlaui-ux-pro-maxupdate-template
Subagents (4)
| db-agent model: inherit | Database operations specialist for SQLite and Entity Framework Core. Use for schema design, migrations, seed data, query optimization, and database troubleshooting. |
| dotnet-reviewer model: sonnet | Expert .NET code reviewer. Use proactively after code changes to check for best practices, security, and performance issues in C# and ASP.NET Core code. |
| security-scanner model: sonnet | Security-focused code reviewer. Use proactively to scan for vulnerabilities, secret leaks, SQL injection, XSS, CSRF issues, and authentication/authorization problems. |
| test-runner model: haiku | Runs and analyzes test results. Use proactively after code changes to verify tests pass. Handles both xUnit unit tests and Playwright E2E tests. |
Hooks (55)
| event | matcher | runs |
|---|---|---|
| UserPromptSubmit | * | INPUT=$(cat); if printf '%s' "$INPUT" | bash "$CLAUDE_PROJECT_DIR/scripts/pipeline-trigger-match.sh" pipeline; then bash "$CLAUDE_PROJECT_DIR/scripts/emit-pipeline-reminder.sh"; fi |
| UserPromptSubmit | * | INPUT=$(cat); if printf '%s' "$INPUT" | bash "$CLAUDE_PROJECT_DIR/scripts/pipeline-trigger-match.sh" analyze; then bash "$CLAUDE_PROJECT_DIR/scripts/emit-analyze-reminder.sh"; fi |
| UserPromptSubmit | * | INPUT=$(cat); if printf '%s' "$INPUT" | bash "$CLAUDE_PROJECT_DIR/scripts/pipeline-trigger-match.sh" clarify; then bash "$CLAUDE_PROJECT_DIR/scripts/emit-clarify-reminder.sh"; fi |
| UserPromptSubmit | * | bash "$CLAUDE_PROJECT_DIR/scripts/feature-pipeline-detect.sh" |
| PreToolUse | Read|Edit|Write|MultiEdit|NotebookEdit|Grep|Glob|Bash | bash "$CLAUDE_PROJECT_DIR/scripts/sensitive-file-guard-hook.sh" |
| PreToolUse | Edit|Write|MultiEdit|NotebookEdit|Bash|AskUserQuestion|mcp__.* | bash "$CLAUDE_PROJECT_DIR/scripts/trust-anchor-guard-hook.sh" |
| PreToolUse | Edit|Write|MultiEdit|NotebookEdit|Bash|mcp__.* | bash "$CLAUDE_PROJECT_DIR/scripts/settings-edit-guard-hook.sh" |
| PreToolUse | Bash | [ -f graphify-out/graph.json ] || { cat >/dev/null; exit 0; }; CMD=$(python3 -c "import json,sys; d=json.load(sys.stdin); print(d.get('tool_input',d).get('command',''))" 2>/dev/null || true); case "$CMD" in *grep*|*rg\ *|*ripgrep*|*find\ *| |
| PreToolUse | Edit|Write|MultiEdit|NotebookEdit | bash "$CLAUDE_PROJECT_DIR/scripts/spec-register-guard-hook.sh" |
| PreToolUse | Edit|Write|MultiEdit|NotebookEdit | bash "$CLAUDE_PROJECT_DIR/scripts/pipeline-state-guard-hook.sh" |
| PreToolUse | Edit|Write|MultiEdit|NotebookEdit | bash "$CLAUDE_PROJECT_DIR/scripts/spec-interview-guard-hook.sh" |
| PreToolUse | Edit|Write|MultiEdit|NotebookEdit | bash "$CLAUDE_PROJECT_DIR/scripts/core-machinery-guard-hook.sh" |
| PreToolUse | Edit|Write|MultiEdit|NotebookEdit | bash "$CLAUDE_PROJECT_DIR/scripts/core-owed-tick-guard-hook.sh" |
| PreToolUse | Bash | bash "$CLAUDE_PROJECT_DIR/scripts/bash-write-guard-hook.sh" |
| PreToolUse | Bash | bash "$CLAUDE_PROJECT_DIR/scripts/destructive-command-guard-hook.sh" |
| PreToolUse | Bash | bash "$CLAUDE_PROJECT_DIR/scripts/stryker-guard-hook.sh" |
| PreToolUse | Edit|Write | bash "$CLAUDE_PROJECT_DIR/scripts/ui-design-hook.sh" |
| PreToolUse | Edit|Write | bash "$CLAUDE_PROJECT_DIR/scripts/sqlite-nfs-safety-hook.sh" |
| PostToolUse | Edit|Write|NotebookEdit | FILE=$(cat | jq -r '.tool_input.file_path // empty' 2>/dev/null); if [ -n "$FILE" ] && echo "$FILE" | grep -qE '\.(cs|csproj)$'; then echo '{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"Reminder: run dotnet build |
| PostToolUse | Edit|Write|NotebookEdit | FILE=$(cat | jq -r '.tool_input.file_path // empty' 2>/dev/null); if [ -n "$FILE" ] && echo "$FILE" | grep -qE '\.(cs|csproj)$'; then echo '{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"Reminder: run dotnet build |
| PostToolUse | Bash | INPUT=$(cat); printf '%s' "$INPUT" | grep -qiE '(Category=UI|playwright|maestro|patrol|integration_test|flutter drive)' || exit 0; CMD=$(echo "$INPUT" | jq -r '.tool_input.command // empty' 2>/dev/null); EXIT=$(echo "$INPUT" | jq -r '.tool_ |
| PostToolUse | Bash | bash "$CLAUDE_PROJECT_DIR/scripts/graphify-fire-hook.sh" |
| PostToolUse | Edit|Write | bash "$CLAUDE_PROJECT_DIR/scripts/spec-md-coverage-reminder-hook.sh" |
| PostToolUse | Edit|Write | bash "$CLAUDE_PROJECT_DIR/scripts/scenario-map-reminder-hook.sh" |
| PostToolUse | Edit|Write | bash "$CLAUDE_PROJECT_DIR/scripts/test-coverage-hook.sh" |
| PostToolUse | Edit|Write | bash "$CLAUDE_PROJECT_DIR/scripts/test-coverage-hook.sh" |
| PostToolUse | Edit|Write | bash "$CLAUDE_PROJECT_DIR/scripts/test-coverage-hook.sh" |
| PostToolUse | Edit|Write | bash "$CLAUDE_PROJECT_DIR/scripts/test-coverage-hook.sh" |
| PostToolUse | Edit|Write | bash "$CLAUDE_PROJECT_DIR/scripts/test-coverage-hook.sh" |
| PostToolUse | Edit|Write | bash "$CLAUDE_PROJECT_DIR/scripts/test-coverage-hook.sh" |
Permissions
deny (7)
Bash(rm -rf *)
Bash(rm -fr *)
Bash(sudo *)
Bash(git push --force*)
Bash(git push *--force*)
Bash(git reset --hard*)
Bash(git clean -f*)
ask (0)
—
allow (2)
Bash
Edit(.claude/skills/**)
Similar rigs
RDW-Labz/project-swarm
Coordinate Claude, Hermes, Qwen and API workers with scoped tasks, up to 32 concurrent jobs, and reviewed integration.
Pragmatist 844 tok · · Q3
selmakcby/claude-agents-skills
Multi-Agent Claude Code setup — 4 uzman ajan (planner · ui-agent · builder · reviewer) + skills + Next.js demo projesi. YouTube Bölüm 1 video materyalleri.
Orchestrator 1.5k tok · · Q3
blackbearhq/claude-config
BlackBear studio shared Claude Code configuration
Pragmatist 3.6k tok · · Q8
yongmmin/review-harness
Review-gated coding harness for Claude Code — one command runs plan → implement → test → review with specialist agents and blocks commits until the reviewer passes. Ships a web-frontend rule profile (TypeScript, React, Next.js); other stack
Skill Collector 2.1k tok · · Q0