eugnmueller-87/claude-blueprint
Seed a Claude Code project with guard rails that hold. Hooks that block secrets deterministically, plus nine CLAUDE.md rules each anchored to a real incident.
stack: Shell
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
Quality 75/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit eugnmueller-87/claude-blueprint/.claude ./rig-claude-blueprint # 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 eugnmueller-87/claude-blueprint/.claude/skills/catchup .claude/skills/catchup $ npx degit eugnmueller-87/claude-blueprint/.claude/skills/claude-md .claude/skills/claude-md $ npx degit eugnmueller-87/claude-blueprint/.claude/skills/context-budget .claude/skills/context-budget $ npx degit eugnmueller-87/claude-blueprint/.claude/skills/db-query .claude/skills/db-query $ npx degit eugnmueller-87/claude-blueprint/.claude/skills/debug-fix .claude/skills/debug-fix $ npx degit eugnmueller-87/claude-blueprint/.claude/skills/eval-agent .claude/skills/eval-agent $ npx degit eugnmueller-87/claude-blueprint/.claude/skills/explain .claude/skills/explain $ npx degit eugnmueller-87/claude-blueprint/.claude/skills/fix-issue .claude/skills/fix-issue $ npx degit eugnmueller-87/claude-blueprint/.claude/skills/incident-rule .claude/skills/incident-rule $ npx degit eugnmueller-87/claude-blueprint/.claude/skills/pr-review .claude/skills/pr-review $ npx degit eugnmueller-87/claude-blueprint/.claude/skills/refactor .claude/skills/refactor $ npx degit eugnmueller-87/claude-blueprint/.claude/skills/secrets-check .claude/skills/secrets-check $ npx degit eugnmueller-87/claude-blueprint/.claude/skills/setup-project .claude/skills/setup-project $ npx degit eugnmueller-87/claude-blueprint/.claude/skills/ship .claude/skills/ship $ npx degit eugnmueller-87/claude-blueprint/.claude/skills/tdd .claude/skills/tdd $ npx degit eugnmueller-87/claude-blueprint/.claude/skills/test-writer .claude/skills/test-writer $ npx degit eugnmueller-87/claude-blueprint/.claude/skills/trace-agent .claude/skills/trace-agent
$ curl -fsSL --create-dirs -o .claude/agents/ai-agent-reviewer.md https://raw.githubusercontent.com/eugnmueller-87/claude-blueprint/master/.claude/agents/ai-agent-reviewer/ai-agent-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/eugnmueller-87/claude-blueprint/master/.claude/agents/code-reviewer/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/data-pipeline-reviewer.md https://raw.githubusercontent.com/eugnmueller-87/claude-blueprint/master/.claude/agents/data-pipeline-reviewer/data-pipeline-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/doc-reviewer.md https://raw.githubusercontent.com/eugnmueller-87/claude-blueprint/master/.claude/agents/doc-reviewer/doc-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-designer.md https://raw.githubusercontent.com/eugnmueller-87/claude-blueprint/master/.claude/agents/frontend-designer/frontend-designer.md $ curl -fsSL --create-dirs -o .claude/agents/performance-reviewer.md https://raw.githubusercontent.com/eugnmueller-87/claude-blueprint/master/.claude/agents/performance-reviewer/performance-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/pr-test-analyzer.md https://raw.githubusercontent.com/eugnmueller-87/claude-blueprint/master/.claude/agents/pr-test-analyzer/pr-test-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/procurement-domain-reviewer.md https://raw.githubusercontent.com/eugnmueller-87/claude-blueprint/master/.claude/agents/procurement-domain-reviewer/procurement-domain-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/eugnmueller-87/claude-blueprint/master/.claude/agents/security-reviewer/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/silent-failure-hunter.md https://raw.githubusercontent.com/eugnmueller-87/claude-blueprint/master/.claude/agents/silent-failure-hunter/silent-failure-hunter.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(**/*.pem)",
"Read(**/*.key)",
"Read(**/*.pfx)",
"Read(**/*.p12)",
"Read(**/id_rsa)",
"Read(**/credentials.json)",
"Read(**/conversations.json)",
"Write(**/.env)",
"Write(**/.env.*)",
"Write(**/secrets/**)",
"Write(**/*.pem)",
"Write(**/*.key)",
"Edit(**/.env)",
"Edit(**/.env.*)",
"Edit(**/secrets/**)",
"Edit(**/*.pem)",
"Edit(**/*.key)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Edit|Write",
"hooks": [
{
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/.claude/hooks/protect-files.sh"
},
{
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/.claude/hooks/warn-large-files.sh"
},
{
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/.claude/hooks/scan-secrets.sh"
}
]
},
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/.claude/hooks/block-dangerous-commands.sh"
}
]
}
]
}
} Skills (17)
catchupclaude-mdcontext-budgetdb-querydebug-fixeval-agentexplainfix-issueincident-rulepr-reviewrefactorsecrets-checksetup-projectshiptddtest-writertrace-agent
Subagents (10)
| ai-agent-reviewer | Use after changes to LLM calls, prompts, agent/tool definitions, LangChain/LangGraph graphs, n8n AI nodes, MCP servers, or RAG pipelines. Reviews prompt-injection exposure, tool-call safety, token/cos |
| code-reviewer | Use after any code change, before committing, or when a diff needs review. Catches real bugs in Python, JS/TS, PowerShell and Bash — off-by-ones, None/null derefs, inverted conditions, races, swallowe |
| data-pipeline-reviewer | Use after changes to pandas/SQL data pipelines, ETL, joins, aggregations, dedupe, or Power BI feed prep. Catches silent data corruption — coercion to NaN, join fan-out, NaN→0 masking, dtype drift, non |
| doc-reviewer | Use after .md, docstring, or README changes — or when code changes may have invalidated existing docs. Cross-references docs against actual source: stale references, wrong Python signatures, missing p |
| frontend-designer | Use when building or restyling any web UI — pages, dashboards, components. Designs tokens-first with a deliberate design principle, avoids generic AI aesthetics, enforces accessibility. States its pla |
| performance-reviewer | Use proactively after changes to hot paths, API endpoints, DB queries, pandas/data transforms, or loops over collections. Finds measurable bottlenecks — N+1 queries, row-wise pandas ops, blocking I/O, |
| pr-test-analyzer | Use when a diff adds or changes tests, or changes behavior without touching tests. Judges whether the pytest tests actually verify the change — catches assertion-free tests, mock theater, tests that c |
| procurement-domain-reviewer | Use after changes to spend/savings calculations, supplier scoring, quote normalization, baseline logic, or compliance checks (LkSG/CSDDD/sanctions) in procurement code (TrueSpend, SpendLens, Hades, He |
| security-reviewer | Use after changes to auth, input handling, queries, file paths, tokens, subprocess/shell calls, deserialization, or crypto — and before deploying any of those. OWASP-style static analysis tuned to Pyt |
| silent-failure-hunter | Use after any change that touches error handling, except/catch blocks, fallbacks, retries, async flows, or pipeline steps — and on every review. Finds code that fails silently: swallowed exceptions, f |
Hooks (8)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Edit|Write | $CLAUDE_PROJECT_DIR/.claude/hooks/protect-files.sh |
| PreToolUse | Edit|Write | $CLAUDE_PROJECT_DIR/.claude/hooks/warn-large-files.sh |
| PreToolUse | Edit|Write | $CLAUDE_PROJECT_DIR/.claude/hooks/scan-secrets.sh |
| PreToolUse | Bash | $CLAUDE_PROJECT_DIR/.claude/hooks/block-dangerous-commands.sh |
| PostToolUse | Edit|Write | $CLAUDE_PROJECT_DIR/.claude/hooks/format-on-save.sh |
| PostToolUse | Edit|Write | $CLAUDE_PROJECT_DIR/.claude/hooks/auto-test.sh |
| SessionStart | startup|resume|clear | $CLAUDE_PROJECT_DIR/.claude/hooks/session-start.sh |
| Notification | * | $CLAUDE_PROJECT_DIR/.claude/hooks/notify.sh |
Permissions
deny (20)
Read(**/.env)
Read(**/.env.*)
Read(**/secrets/**)
Read(**/*.pem)
Read(**/*.key)
Read(**/*.pfx)
Read(**/*.p12)
Read(**/id_rsa)
Read(**/credentials.json)
Read(**/conversations.json)
Write(**/.env)
Write(**/.env.*)
Write(**/secrets/**)
Write(**/*.pem)
Write(**/*.key)
Edit(**/.env)
Edit(**/.env.*)
Edit(**/secrets/**)
Edit(**/*.pem)
Edit(**/*.key)
ask (0)
—
allow (27)
Bash(pytest *)
Bash(python -m pytest *)
Bash(ruff check *)
Bash(ruff format *)
Bash(mypy *)
Bash(python -m venv *)
Bash(pip install -r *)
Bash(pip install -e *)
Bash(pip list)
Bash(pip show *)
Bash(npm run lint *)
Bash(npm run test *)
Bash(npm run build)
Bash(npx tsc --noEmit)
Bash(git status)
Bash(git diff *)
Bash(git log *)
Bash(git branch *)
Bash(git show *)
Bash(git add *)
Bash(git commit *)
Bash(git fetch *)
Bash(git switch *)
Bash(git checkout *)
Bash(gh pr *)
Bash(gh issue *)
Bash(gh run *)
Similar rigs
poshan0126/dotclaude
The standard .claude/ folder structure for everyday development.
Fort Knox 1.7k tok · · Q23
peterbamuhigire/chwezi-dev-engine
Software Dev't Engine for coding. Production-grade skills system for web apps & mobile architecture, APIs, databases, web, mobile, AI, security, UX, SaaS, and ERP engineering. Encodes reusable engineering judgment through layered baseline
Orchestrator 6.8k tok · · Q5
ZaaliMohamed123/evolving-claude
A self-improving global Claude Code setup: 10 subagents, on-demand skills, safety hooks, three-tier memory, and a config feedback loop.
Orchestrator 2.2k tok · · Q5
aware-aeco/aware
Open-source agentic substrate for AECO. Apps are text. AI is the runtime.
Orchestrator 4.4k tok · · Q10