Skip to content

thedotmack/claude-mem / plugin/skills/agent-cost-report

agent-cost-report

Verified

Believable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.

FileKindSize
.gitignoreother100 B
CHECKSUMS.txtmarkdown2.1 KB
SKILL.mdskill md21.3 KB
VERIFICATION.mdmarkdown12.3 KB
scripts/acr.pyexecutablescript12.2 KB
scripts/acr/__init__.pyscript105 B
scripts/acr/behavior.pyscript17.5 KB
scripts/acr/classify.pyscript5.5 KB
scripts/acr/costs.pyscript6.3 KB
scripts/acr/devices.pyscript5.4 KB
scripts/acr/evidence.pyscript9.2 KB
scripts/acr/labels.pyscript7.6 KB
scripts/acr/measure.pyscript5.6 KB
scripts/acr/mistakes.pyscript23.1 KB
scripts/acr/owner.pyscript2.9 KB
scripts/acr/patterns.pyscript26.0 KB
scripts/acr/period.pyscript3.8 KB
scripts/acr/prices.pyscript5.0 KB
scripts/acr/render.pyscript52.7 KB
scripts/acr/rollup.pyscript31.7 KB
scripts/acr/rules.jsonconfig3.5 KB
scripts/acr/rules.pyscript4.5 KB
scripts/acr/sample.pyscript3.6 KB
scripts/acr/snapshot.pyscript2.0 KB
scripts/acr/sync.pyscript3.7 KB
scripts/acr/transcripts.pyscript7.4 KB
scripts/acr/wins.pyscript21.0 KB
scripts/tests/_db.pyscript3.6 KB
scripts/tests/_paths.pyscript337 B
scripts/tests/fixtures/codex/sessions/2026/09/18/rollout-codex-1.jsonlother664 B
scripts/tests/fixtures/make_report_fixtures.pyscript2.0 KB
scripts/tests/fixtures/prices_sample.jsonconfig611 B
scripts/tests/fixtures/projects/-workspace-proj-a/sess-aaaa.jsonlother2.9 KB
scripts/tests/fixtures/projects/-workspace-proj-b/sess-bbbb.jsonlother537 B
scripts/tests/fixtures/report-1day.jsonconfig20.1 KB
scripts/tests/fixtures/report-30day.jsonconfig48.1 KB
scripts/tests/fixtures/report-7day.jsonconfig29.1 KB
scripts/tests/fixtures/report-empty.jsonconfig13.8 KB
scripts/tests/fixtures/report-session.jsonconfig16.6 KB
scripts/tests/test_behavior.pyscript29.6 KB
scripts/tests/test_devices.pyscript5.9 KB
scripts/tests/test_labels.pyscript8.6 KB
scripts/tests/test_measure.pyscript6.8 KB
scripts/tests/test_period.pyscript7.0 KB
scripts/tests/test_prices.pyscript5.3 KB
scripts/tests/test_render.pyscript12.1 KB
scripts/tests/test_render_encoding.pyscript1.5 KB
scripts/tests/test_rollup.pyscript19.3 KB
scripts/tests/test_snapshot.pyscript2.8 KB
scripts/tests/test_sync.pyscript2.5 KB
scripts/tests/test_transcript_encoding.pyscript2.7 KB
scripts/tests/test_transcripts.pyscript8.1 KB
scripts/tests/test_wins.pyscript15.7 KB
verification/precision-2026-09-26.jsonconfig308 B

scripts/tests/fixtures/make_report_fixtures.py

View on GitHub
"""Regenerates tests/fixtures/report-*.json (1-day, 7-day, 30-day, empty period, single session) from the
test_rollup fixture DB, so the renderer tests never depend on the live database. Run from scripts/tests:
    python3 fixtures/make_report_fixtures.py
"""
import copy
import json
import os
import sqlite3
import sys
import tempfile

sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import _paths  # noqa: E402,F401
import test_rollup as tr  # noqa: E402
from acr import evidence, period, rollup  # noqa: E402

EMPTY_GLOB = os.path.join(tempfile.mkdtemp(prefix="acr-noglob-"), "**", "*.jsonl")


def build(fx, start, end, scope=None, rows=None):
    W = period.resolve_window(start, end, now=tr.NOW) if start else None
    db = sqlite3.connect(fx.dbp); db.row_factory = sqlite3.Row
    try:
        sc = scope or evidence.Scope("period", S=W.start_epoch_ms, E=W.end_epoch_ms)
        usage = dict(window=(W.block() if W else period.session_block(sc.session, now=tr.NOW)), rows=copy.deepcopy(fx.rows if rows is None else rows))
        report, _, _ = rollup.build(usage, tr.PRICES, db, sc, usage["window"], now=tr.NOW, use_gh=False, remote=lambda cwd: None, glob_pattern=EMPTY_GLOB)
        return report
    finally:
        db.close()


def main():
    fx = tr.Fixture("setUp"); fx.setUp()
    try:
        out = {"report-1day": build(fx, "2026-09-18", "2026-09-19"), "report-7day": build(fx, "2026-09-18", "2026-09-25"),
               "report-30day": build(fx, "2026-09-01", "2026-10-01"), "report-empty": build(fx, "2026-08-01", "2026-08-03", rows=[]),
               "report-session": build(fx, None, None, evidence.Scope("session", session="cs1"))}
        for name, rep in out.items():
            with open(os.path.join(_paths.FIXTURES, name + ".json"), "w") as fh: json.dump(rep, fh, indent=1, default=str, sort_keys=True)
            print(name, rep["totals"]["sessions"], len(rep["by_day"]), rep["spend"]["agent_estimated_usd"])
    finally:
        fx.tearDown()


if __name__ == "__main__":
    main()
deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
backup-setupthedotmack/claude-memSet up, check, or restore local claude-mem database snapshots. Use when the user says "set up backups", "back up my memories", "backup status", or "restore my database".Stars: 118kUpdated Claude CodeCodexVerifiedInstall