twelfth-puerperium297/tokenoptim
Reduce LLM token usage by 40–75 percent with this CLI tool and SDK. Optimize prompts for Claude, OpenAI, and other models without needing an API key.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit twelfth-puerperium297/tokenoptim/skills ./rig-tokenoptim/skills 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 twelfth-puerperium297/tokenoptim/skills/ancient .claude/skills/ancient $ npx degit twelfth-puerperium297/tokenoptim/skills/full .claude/skills/full $ npx degit twelfth-puerperium297/tokenoptim/skills/lite .claude/skills/lite $ npx degit twelfth-puerperium297/tokenoptim/skills/standard .claude/skills/standard $ npx degit twelfth-puerperium297/tokenoptim/skills/ultra .claude/skills/ultra
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (5)
Similar rigs
zhnt/loushang
AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.
Minimalist 1.8k tok · · Q20
yard-labs/yl-audit
Read-only app audits for Claude Code: security, delivery and reliability across the live app, code, Supabase, CI/CD and observability, merged into one report.
Pragmatist 532 tok · · Q0
Dev-Wesley-13/git-parity
Claude Code plugin: keep local and remote git branches in parity across many repositories. Fast-forward only, push and PR on confirmation, one short report.
Pragmatist 548 tok · · Q0
yushman/slimspec
Lightweight spec-driven development for Claude Code: explore → plan → apply → verify → ground, with mandatory red-green TDD and specs as module CLAUDE.md files
Skill Collector 1.9k tok · · Q0