aniteshdharam/claude-token-policy
A Claude Code plugin that cuts your token bill by shrinking context per call, not by picking a cheaper model: a policy skill, enforcing hooks, and a census script that measures your own transcripts.
stack: Python
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
Copy this rig
# review before running: this installs third-party code $ npx degit aniteshdharam/claude-token-policy/agents ./rig-claude-token-policy/agents $ npx degit aniteshdharam/claude-token-policy/commands ./rig-claude-token-policy/commands $ npx degit aniteshdharam/claude-token-policy/skills ./rig-claude-token-policy/skills $ npx degit aniteshdharam/claude-token-policy/hooks ./rig-claude-token-policy/hooks
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 aniteshdharam/claude-token-policy/skills/token-policy .claude/skills/token-policy $ curl -fsSL --create-dirs -o .claude/agents/builder.md https://raw.githubusercontent.com/aniteshdharam/claude-token-policy/main/agents/builder.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/aniteshdharam/claude-token-policy/main/agents/reviewer.md
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 (1)
Subagents (2)
| builder model: sonnet | Fast-tier build agent. Use for one bounded slice of ordinary building (a feature slice, a fix round, a rebase, a docs pass) when the main session hands it a written brief. Builds only; never reviews i |
| reviewer model: opus | Strong-tier review agent at high effort. Use for one bounded review of ordinary work (a fresh read of a delta, a re-read after a fix round, the security read of an ordinary change) when the main sessi |
Slash commands (1)
/token-census
Similar rigs
Gildaciolopes/agentic-dev-stack
Smart vibe coding with Claude Code: multi-agent orchestration (Opus plans; Sonnet, Haiku, Gemini, Codex and free models execute), Spec Kit SDD, caveman + RTK + graphify token savings, sandboxed secrets, self-healing free models and a Hermes
Minimalist 1.2k tok · · Q10
brackenjoe/agent-infrastructure
A guide for AI agent set up. A manager, a cheaper builder for code, any agents for other repetitive tasks, and the governance to keep them in line.
Minimalist 1.4k tok · · Q18
brenocq/capcom
Mission control for your Claude Code spend
Orchestrator 2.1k tok · · Q8
OMOCHInoHOSHI/dotfiles-claude
.claude
Minimalist 177 tok · · Q19