メニュー
Use when you want to see token consumption by task type, model, one-shot rate, or USD cost — observability dashboard for Claude Code sessions
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | codeburn |
| description | Use when you want to see token consumption by task type, model, one-shot rate, or USD cost — observability dashboard for Claude Code sessions |
| user-invocable | true |
| disable-model-invocation | true |
Reads directly from ~/.claude/projects/ (no API keys, no wrappers) and renders a TUI dashboard showing where tokens go.
Complementary to rtk: rtk reduces tokens spent (efficiency); codeburn shows which tasks need optimization most (observability). Together they close the feedback loop.
codeburn # Interactive TUI dashboard (keyboard navigation)
codeburn today # Today's sessions only
codeburn report -p 30days # 30-day rolling window
codeburn report --project <name> # Filter by project
codeburn export --format csv # Export for further analysis
codeburn export --format json # JSON output
| Metric | Why it matters |
|---|---|
| Tokens by task type (13 categories) | Find which work type is most expensive |
| One-shot rate per task type | % tasks done in 1 API call vs retry loop |
| Per-model breakdown | Cost difference between Opus and Sonnet for your actual tasks |
| USD cost estimate | Real spend per session / project |
| Input vs output token split | Output tokens cost 3-5× more than input |
refactor · bug-fix · feature · test · docs · review · debug · config · migration · research · security · cleanup · other
codeburn report → find low one-shot rate task type
→ add context/rules for that category in CLAUDE.md or claude/*.md
→ rtk reduces token output on those commands
→ re-run codeburn to verify improvement
Signal: If one-shot rate < 50% for a task type, it needs more upfront context or better rules.
npm install -g codeburn # Global install
npx codeburn # One-shot without global install
Requires Node.js 18+.
Route a codebase question to the right tool — structural graph, semantic search, or risk analysis. Use when you need to find or understand code without knowing exact file names.
Auto-configure CLAUDE.md and claude/ knowledge docs for a new project. Use when setting up Brain Bootstrap in a new repository. Discovers the codebase, fills in templates, and writes project-specific configuration.
Build the project and verify it compiles cleanly. Use after making changes to confirm nothing is broken before running tests. Reads the build command from claude/build.md.
Save session state before context gets full or before ending. Writes current task state, branch, and loaded docs to claude/tasks/todo.md so the next session can resume cleanly.
Remove all git worktrees for merged branches. Accepts --dry-run to preview. Use after merging PRs or for weekly maintenance.
Clean workspace — build artifacts, dependencies, caches, Docker volumes, or temp files. Accepts arguments like build, deps, all, cache, docker, tasks, reinstall.