costslisted

Report API-equivalent costs for Claude Code usage — per chat, skill, subagent, project, model, day, git branch, or PR. Collects fresh data from session transcripts, then reports from the cost ledger. Triggers on 'what did this chat cost', 'how much did X cost', 'costs this month', 'token spend', 'cost report', 'what did that PR/branch cost'.
spikelab/multiplai-cc-mktplace · ★ 0 · AI & Automation · score 66

Install: claude install-skill spikelab/multiplai-cc-mktplace

# Costs — Usage Cost Accounting Reports what multiplai usage *would have billed* at Claude API list prices, from the append-only cost ledger in `<data_dir>/costs/`. Two scripts: - `collect_costs.py` — incrementally scans `$CLAUDE_CONFIG_DIR/projects/**/*.jsonl` and appends priced records to the ledger. Idempotent; first run is a full backfill, later runs read only new bytes. - `costs_report.py` — aggregates the ledger. ## Steps 1. **Collect first** so the report includes recent sessions: ``` uv run --project "${CLAUDE_PLUGIN_ROOT}/scripts" "${CLAUDE_PLUGIN_ROOT}/scripts/collect_costs.py" ``` 2. **Report** based on what the user asked: | User asks | Command | |---|---| | overall / this month | `costs_report.py` | | a specific month | `costs_report.py --month YYYY-MM` | | this chat / a session | `costs_report.py --session <id-prefix>` (current session id is in the transcript filename) | | per skill | `costs_report.py --all --by skill` | | per project / model / day / component | `costs_report.py --by project\|model\|day\|component` | | per branch | `costs_report.py --all --by branch` | | one branch | `costs_report.py --branch <name>` (reads all months; `--branch "(none)"` for unattributed) | | a PR | resolve the branch with `gh`, then `--branch` — see below | | cost per completed task | `costs_report.py --all --group task --pr-join --project-dir <repo>` | | cost per buildme block | `costs_report.py --all --group build --proje