~ / rigs / Sabeekhann / cc-token-meter

Sabeekhann/cc-token-meter

Private, local Claude Code usage intelligence track tokens, estimated cost, cache efficiency, budgets, projects, and live sessions with zero telemetry.

↗ GitHub ★ 4 Apache-2.0 updated today project Claude Code
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~7.3k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit Sabeekhann/cc-token-meter/.claude ./rig-cc-token-meter  # 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.

$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/Sabeekhann/cc-token-meter/main/.claude/agents/architect.md
$ curl -fsSL --create-dirs -o .claude/agents/dashboard-ui.md https://raw.githubusercontent.com/Sabeekhann/cc-token-meter/main/.claude/agents/dashboard-ui.md
$ curl -fsSL --create-dirs -o .claude/agents/data-layer.md https://raw.githubusercontent.com/Sabeekhann/cc-token-meter/main/.claude/agents/data-layer.md
$ curl -fsSL --create-dirs -o .claude/agents/heuristics-dev.md https://raw.githubusercontent.com/Sabeekhann/cc-token-meter/main/.claude/agents/heuristics-dev.md
$ curl -fsSL --create-dirs -o .claude/agents/qa-tester.md https://raw.githubusercontent.com/Sabeekhann/cc-token-meter/main/.claude/agents/qa-tester.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Subagents (5)

architectRead-only structural reviewer for cc-token-meter — file placement, duplication, module/pure-function boundary violations, dependency footprint. Use after a feature change lands, before considering it
dashboard-uiOwns public/dashboard.html, public/dashboard.css, public/dashboard.js. Use for any frontend/visual/interaction change to the dashboard.
data-layerOwns src/ingest/* (discover.js, parser.js, store.js, aggregate.js) and src/server/summary.js, routes.js, sse.js. Use for backend/data work — new ingestion fields, aggregation logic, or API/SSE payload
heuristics-devOwns src/heuristics/* and src/budget/alerts.js. Use for adding/changing tip-generating heuristics or budget-alert logic.
qa-testerWrites and runs node:test fixture tests for cc-token-meter, following the pattern in CONTRIBUTING.md. Use after a heuristics or data-layer change to add/verify test coverage.

Similar rigs

copied ✓