usage
Use when user asks token/cost/usage of Codex. Zero-token disk read; not for product features.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Use when user asks token/cost/usage of Codex. Zero-token disk read; not for product features.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | usage |
| description | Use when user asks token/cost/usage of Codex. Zero-token disk read; not for product features. |
See Codex usage and activity breakdown without spending any tokens.
Before large reads, broad searches, or loops, estimate context cost with
scripts/work_visibility.py. Always say usage estimates are approximate.
Compact tool output into receipts instead of pasting full logs into chat.
python scripts/codeburn.py status
Compact one-liner with today's sessions, tokens, and month total. Zero tokens — reads session files directly from disk.
python scripts/codeburn.py today
Today's sessions, by-model and by-activity breakdown with one-shot rate, top tools.
python scripts/codeburn.py report # last 7 days
python scripts/codeburn.py report -p 30d # last 30 days
python scripts/codeburn.py report -p all # entire history
python scripts/codeburn.py report --format json
python scripts/codeburn.py daemon
Starts web dashboard at http://localhost:8765.
Period tabs (Today/7d/30d/Month/All), model/activity/tool tables, daily trend chart.
Stop with python scripts/codeburn.py stop.
Background dashboard or scans must be visible, stoppable, bounded, and receipt-producing. Do not leave indefinite hidden workers running.
python scripts/codeburn.py export # JSON (7 days)
python scripts/codeburn.py export -f csv # CSV
python scripts/codeburn.py export -p all # full history
$usage for compact status check (0 tokens)$usage + today for daily review$usage + daemon for live web monitoring$usage + report for deep analysisFor Claude Code, Cursor, or other providers — use npx codeburn.
When this skill's job is finished:
Use when a plan or concrete tasks exist and user said build/go/implement. Not to invent scope or claim done without verify.
Use when goal/spec is clear and you need ordered tasks before writing code. Not while still clarifying.
Use when about to claim done/works/fixed, or user asks test/check/prove. Run evidence; not for pure planning chat.
Use when another installed plugin/skill may do the job better, or to route specialists. ACC stays workflow owner.
Use when user wants an explicit recorded decision or blocker saved to artifacts. Not silent monitoring.
Use when request is too vague to plan or build. Not when goal and constraints are already clear.