Sagargupta16/claude-cost-optimizer
Save 30-60% on Claude Code costs -- proven strategies, real benchmarks, copy-paste configs, and interactive tools
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 Sagargupta16/claude-cost-optimizer/.claude ./rig-claude-cost-optimizer # 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 Sagargupta16/claude-cost-optimizer/plugins/cost-mode/skills/cost-mode .claude/skills/cost-mode 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(./node_modules/**)",
"Read(./dist/**)",
"Read(./build/**)",
"Read(./tools/vscode-extension/out/**)",
"Read(*.vsix)",
"Read(*.tsbuildinfo)",
"Read(*.lock)",
"Read(package-lock.json)",
"Read(pnpm-lock.yaml)",
"Read(./__pycache__/**)",
"Read(*.pyc)",
"Read(./.ruff_cache/**)",
"Read(./.pytest_cache/**)",
"Read(./coverage/**)",
"Read(./htmlcov/**)",
"Read(.coverage)",
"Read(*.log)",
"Read(./.venv/**)",
"Read(./venv/**)",
"Read(./.vscode/**)",
"Read(./.idea/**)",
"Read(./.git/**)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": ".*",
"hooks": [
{
"type": "command",
"command": "bash hooks/budget-tracker.sh"
},
{
"type": "command",
"command": "bash hooks/cost-logger.sh"
}
]
}
]
}
} Skills (1)
Hooks (3)
| event | matcher | runs |
|---|---|---|
| PreToolUse | .* | bash hooks/budget-tracker.sh |
| PreToolUse | .* | bash hooks/cost-logger.sh |
| Stop | * | bash hooks/session-summary.sh |
Permissions
deny (24)
Read(.env)
Read(.env.*)
Read(./node_modules/**)
Read(./dist/**)
Read(./build/**)
Read(./tools/vscode-extension/out/**)
Read(*.vsix)
Read(*.tsbuildinfo)
Read(*.lock)
Read(package-lock.json)
Read(pnpm-lock.yaml)
Read(./__pycache__/**)
Read(*.pyc)
Read(./.ruff_cache/**)
Read(./.pytest_cache/**)
Read(./coverage/**)
Read(./htmlcov/**)
Read(.coverage)
Read(*.log)
Read(./.venv/**)
Read(./venv/**)
Read(./.vscode/**)
Read(./.idea/**)
Read(./.git/**)
ask (0)
—
allow (11)
Read(**)
Bash(python tools/claude-rate/rate.py:*)
Bash(python tools/badge-generator/generate.py:*)
Bash(python scripts/check-pricing-sync.py:*)
Bash(python scripts/check-links.py:*)
Bash(python -m compileall:*)
Bash(npm run build)
Bash(npm run lint)
Bash(npx tsc:*)
Bash(git status)
Bash(git diff:*)
Similar rigs
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 ·
FlorianBruniaux/claude-code-ultimate-guide
The most comprehensive Claude Code guide: agentic workflows, hooks, skills, MCP servers, quizzes, and production-ready templates. 430K+ lines.
Fort Knox 33.8k tok ·
trailofbits/claude-code-config
Opinionated defaults, documentation, and workflows for Claude Code at Trail of Bits
Fort Knox 0 tok ·