菜单
AI spend analytics — see where your token budget goes by task, model, tool, and project across 31 AI coding tools including Claude Code. Use when the user asks about AI costs, token usage, spend breakdown, or wants to optimize their AI budget.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.
Stages all changes and generates a lean Conventional Commits message via caveman-commit — user reviews and commits manually. Triggers on any commit intent: "commit", "stage my changes", "ready to push", "let's commit", "make a commit", "commit this", "push changes", "squash and commit", or any variation. Use whenever the user signals they're done with changes and ready to commit, even if they don't mention "message" or "caveman". Does NOT run git commit — outputs a ready-to-run command for the user to execute after review.
Autonomous ML research - agent modifies GPT training code, runs 5-min experiments, keeps improvements
Always use browser-harness for any web interaction: automation, scraping, testing, or site/app work.
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
A standalone adversarial PLAN-review loop where Claude Code (builder) and OpenAI Codex (read-only critic) tag-team an implementation plan before any code is written. Use this when you ALREADY have a plan or a clear idea and just want the cross-model stress-test — no requirements interview first. Claude drafts/loads the plan into PLAN.md, Codex reviews it in a read-only sandbox and returns VERDICT:APPROVED or VERDICT:REVISE, Claude revises and re-submits to the SAME Codex session (context preserved) until APPROVED or a configurable MAX_ROUNDS cap is hit. Human approves the converged plan before code. Use when the user says "/codex-review", "codex review my plan", "have Codex review my plan", "argue this plan with Codex", "adversarial plan review", "make Claude and Codex argue/fight over the plan", or is about to build something high-stakes (auth, schema, concurrency, migrations, payments) and wants a second-model sanity check on the PLAN before implementation. For a guided requirements interview BEFORE the rev
| name | codeburn |
| description | AI spend analytics — see where your token budget goes by task, model, tool, and project across 31 AI coding tools including Claude Code. Use when the user asks about AI costs, token usage, spend breakdown, or wants to optimize their AI budget. |
See where your AI spend goes — by task, model, tool, and project, across 31 AI tools (Claude Code, Codex, Cursor, Gemini CLI, Cline, and more).
# Interactive dashboard (last 7 days)
npx codeburn
# Or install globally (faster)
npm install -g codeburn
codeburn
# Dashboard views
codeburn # Interactive TUI — last 7 days (default)
codeburn today # Today's usage
codeburn month # This calendar month
# One-liner status
codeburn status # Today + month totals
codeburn status --format json # Same as JSON
# Reports
codeburn overview # Plain-text monthly summary
codeburn report -p 30days # Rolling 30-day window
codeburn report -p all # All recorded sessions
codeburn report --from 2026-04-01 --to 2026-04-30 # Date range
codeburn report --format json # Full data as JSON
# Export
codeburn export # CSV (today, 7d, 30d)
codeburn export -f json # JSON export
# Analysis
codeburn optimize # Scan for waste + copy-paste fixes (30d)
codeburn optimize -p week # Scope to last 7 days
codeburn compare # Side-by-side model comparison
# Web dashboard with charts
codeburn web # http://localhost:4747
# Filter by provider or project
codeburn report --provider claude
codeburn report --project my-app
| Category | What triggers it |
|---|---|
| Coding | Edit, Write tools |
| Debugging | Error/fix keywords + tool usage |
| Feature Dev | "add", "create", "implement" |
| Refactoring | "refactor", "rename", "simplify" |
| Testing | pytest, vitest, jest in Bash |
| Exploration | Read, Grep, WebSearch without edits |
| Planning | EnterPlanMode, TaskCreate tools |
| Delegation | Agent tool spawns |
| Git Ops | git push/commit/merge in Bash |
| Build/Deploy | npm build, docker, pm2 |
| Brainstorming | "brainstorm", "what if", "design" |
| Conversation | No tools, pure text exchange |
| General | Skill tool, uncategorized |
| Signal | What it might mean |
|---|---|
| Cache hit < 80% | System prompt or context not stable |
Lots of Read calls per session | Agent re-reading same files, missing context |
| Low 1-shot rate (Coding 30%) | Agent struggling with edits, retry loops |
| Opus dominating cost on small turns | Overpowered model for simple tasks |
| Conversation category dominant | Agent talking instead of doing |
| No MCP usage shown | Either not using MCP, or config is broken |
CodeBurn reads Claude Code session files from:
~/.claude/projects/<sanitized-path>/<session-id>.jsonl
Each session carries: model name, token usage (input/output/cache read/cache write), tool_use blocks, timestamps. No data leaves your machine.
Multiple Claude config dirs: set CLAUDE_CONFIG_DIRS (: on POSIX, ; on Windows).
Already installed in this project. On fresh clones, setup.sh installs via:
npm install -g codeburn
Verify:
codeburn --version
npm install -g codeburn@latest
# Or via /update-all skill