design-and-deliver/claude-code-autoconfig
Intelligent, self-configuring setup for Claude Code 👉 npx claude-code-autoconfig
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
GUARDRAILS
4/5
Blocks destructive commands · Protects secrets · Pre-tool screening hook · No YOLO mode · details
Copy this rig
# review before running: this installs third-party code
$ npx degit design-and-deliver/claude-code-autoconfig/.claude ./rig-claude-code-autoconfig # 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 design-and-deliver/claude-code-autoconfig/.claude/skills/plan-authoring .claude/skills/plan-authoring $ curl -fsSL --create-dirs -o .claude/agents/create-retro-item.md https://raw.githubusercontent.com/design-and-deliver/claude-code-autoconfig/main/.claude/agents/create-retro-item.md $ curl -fsSL --create-dirs -o .claude/agents/docs-refresh.md https://raw.githubusercontent.com/design-and-deliver/claude-code-autoconfig/main/.claude/agents/docs-refresh.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": [
"Read(./.env)",
"Read(./.env.*)",
"Read(./secrets/**)",
"Read(./**/credentials.*)",
"Read(./**/*.pem)",
"Read(./**/*.key)",
"Bash(rm -rf *)",
"Bash(curl *)",
"Bash(wget *)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "node \"${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/auto-guard.js\""
},
{
"type": "command",
"command": "node \"${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/feedback-rule-check.js\""
}
]
}
]
}
} Skills (1)
Subagents (2)
| create-retro-item model: haiku | Writes a fully-scoped retro story file into .claude/retro/ when tech debt, friction, or an improvement opportunity is worth tracking. Use proactively after finishing a task; hand it title, problem, cr |
| docs-refresh | — |
Hooks (13)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | node "${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/migrate-feedback.js" |
| SessionStart | * | node "${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/terminal-title.js" |
| UserPromptSubmit | * | node "${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/terminal-title.js" |
| Stop | * | cd "${CLAUDE_PROJECT_DIR:-.}" 2>/dev/null; if [ -n "$(find .git/.cc-commit-active -mmin -5 2>/dev/null)" ]; then exit 0; fi; f=$(git status --porcelain 2>/dev/null | grep -c .); l=$(git diff HEAD --numstat 2>/dev/null | awk '{s+=$1+$2} END |
| Stop | * | node "${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/terminal-title.js" |
| Stop | * | node "${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/arcade-beeps.js" |
| Notification | permission_prompt | node "${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/terminal-title.js" |
| Notification | permission_prompt | node "${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/arcade-beeps.js" |
| Notification | idle_prompt | node "${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/terminal-title.js" --idle-rescue |
| PreToolUse | Bash | node "${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/auto-guard.js" |
| PreToolUse | Bash | node "${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/feedback-rule-check.js" |
| PostToolUse | Bash | node "${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/mark-commit-active.js" |
| PostToolUse | Bash|Write|Edit|MultiEdit|NotebookEdit|WebFetch|WebSearch|Task|Agent|AskUserQuestion | node "${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/terminal-title.js" |
Slash commands (33)
/abort-plan/analyze-session/autoconfig-update/autoconfig/check-commit/commit-and-push/continue/cost-compare/create-wip-report/disable-auto-mode/disable-status-beeps/enable-auto-mode/enable-retro/enable-status-beeps/eod-report/extract-rules/fleet/gimme-one-liner/gls/land/migrate-new-session/plan-progress/recover-context/refactor/restore-after-reboot/show-docs/submit-claude-code-github-issue/sync-claude-md/sync-worktrees/test/token-saver-rationale/usage-report/whats-happening
Permissions
deny (9)
Read(./.env)
Read(./.env.*)
Read(./secrets/**)
Read(./**/credentials.*)
Read(./**/*.pem)
Read(./**/*.key)
Bash(rm -rf *)
Bash(curl *)
Bash(wget *)
ask (0)
—
allow (43)
Read(./**)
Edit(./**)
Glob
Grep
WebSearch
WebFetch
Bash(npm test)
Bash(npm test *)
Bash(npm run dev)
Bash(npm run build)
Bash(npm run lint)
Bash(npm run lint:fix)
Bash(npm run typecheck)
Bash(npm run test)
Bash(npm run test:*)
Bash(npm run validate)
Bash(git status)
Bash(git status *)
Bash(git diff *)
Bash(git add *)
Bash(git commit *)
Bash(git push *)
Bash(git pull)
Bash(git pull *)
Bash(git checkout *)
Bash(git branch *)
Bash(node .claude/*)
Bash(python3 *)
Bash(npx claude-code-autoconfig*)
Bash(npm pack *)
Bash(tar *)
Bash(mktemp *)
Bash(find ./*)
Bash(ls *)
Bash(dir *)
Bash(mkdir *)
Bash(mkdir -p *)
Bash(start *)
Bash(start .claude *)
Bash(open *)
Bash(open .claude *)
Bash(xdg-open *)
Bash(xdg-open .claude *)
Similar rigs
JakeSelby/model-citizen
The control plane for your coding agents, however you run them. One checkout of rules, skills, subagents, hooks and stances, projected into Claude Code and Codex with your own primitives: hook-enforced guardrails, usage telemetry, cost post
Skill Collector 3.1k tok ·
attilaszasz/sdd-pilot
Replace chaotic AI code generation with a disciplined, spec-driven workflow. SDD Pilot enforces structured development phases and quality gates, leveraging AI agents to conduct online research for best practices and plan your architecture b
Orchestrator 5.3k tok ·
ruvnet/ruflo
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native
Fort Knox 35.3k tok ·
Donchitos/Claude-Code-Game-Studios
Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.
Fort Knox 11.6k tok ·