thedotmack/claude-mem / claude-mem-grok-bot/skills/agent-cost-report
agent-cost-report
VerifiedBelievable 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.
| File | Kind | Size |
|---|---|---|
| .gitignore | other | 100 B |
| CHECKSUMS.txt | markdown | 2.1 KB |
| SKILL.md | skill md | 21.3 KB |
| scripts/acr.py | script | 12.2 KB |
| scripts/acr/__init__.py | script | 105 B |
| scripts/acr/behavior.py | script | 17.5 KB |
| scripts/acr/classify.py | script | 5.5 KB |
| scripts/acr/costs.py | script | 6.3 KB |
| scripts/acr/devices.py | script | 5.4 KB |
| scripts/acr/evidence.py | script | 9.2 KB |
| scripts/acr/labels.py | script | 7.6 KB |
| scripts/acr/measure.py | script | 5.6 KB |
| scripts/acr/mistakes.py | script | 23.1 KB |
| scripts/acr/owner.py | script | 2.9 KB |
| scripts/acr/patterns.py | script | 26.0 KB |
| scripts/acr/period.py | script | 3.8 KB |
| scripts/acr/prices.py | script | 5.0 KB |
| scripts/acr/render.py | script | 52.7 KB |
| scripts/acr/rollup.py | script | 31.7 KB |
| scripts/acr/rules.json | config | 3.5 KB |
| scripts/acr/rules.py | script | 4.5 KB |
| scripts/acr/sample.py | script | 3.6 KB |
| scripts/acr/snapshot.py | script | 2.0 KB |
| scripts/acr/sync.py | script | 3.7 KB |
| scripts/acr/transcripts.py | script | 7.4 KB |
| scripts/acr/wins.py | script | 21.0 KB |
scripts/acr/sync.py
View on GitHub"""Phase 7.2: copy + checksum sync of the skill (SKILL.md, CHECKSUMS.txt and runtime files under scripts/)
from the plugin dir (source of truth) to the house copy and the four mirror plugins (G2: mirrors carry
the skill as byte copies, tracked in git). `sync-check` reports drift and exits 1; `--write` copies
plugin -> destinations and re-checks. Destinations live in one place (DESTINATIONS) and can be
overridden with --dest. Nothing outside that list is ever written.
"""
import hashlib
import os
import shutil
SKILL_DIR = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) # plugin/skills/agent-cost-report
REPO_ROOT = os.path.dirname(os.path.dirname(os.path.dirname(SKILL_DIR))) # the checkout holding plugin/
MIRRORS = ("claude-mem-cursor", "claude-mem-grok-bot", "cowork", "openclaw")
HOUSE_COPY = os.path.expanduser("~/agent-data/workflows/agent-cost-report")
CHECKSUMS = "CHECKSUMS.txt"
SKIP_DIRS = {"__pycache__", ".chrome-profile", "tests"}
SKIP_FILES = {CHECKSUMS}
def destinations(repo_root=REPO_ROOT, house=HOUSE_COPY):
return [house] + [os.path.join(repo_root, m, "skills", "agent-cost-report") for m in MIRRORS]
def shipped_files(root=SKILL_DIR):
"""Relative paths of every shipped file: SKILL.md plus scripts/** (no tests, caches or checksum file).
Always POSIX-separated: CHECKSUMS.txt is sha256sum-compatible and the mirrors are byte copies,
so a Windows run must not write `scripts\\acr.py` where the committed manifest says `scripts/acr.py`.
"""
out = []
for dirpath, dirs, files in os.walk(root):
dirs[:] = sorted(d for d in dirs if d not in SKIP_DIRS and (dirpath != root or d == "scripts"))
for f in sorted(files):
rel = os.path.relpath(os.path.join(dirpath, f), root).replace(os.sep, "/")
if dirpath == root and f not in ("SKILL.md",): continue
if f in SKIP_FILES or f.endswith(".pyc"): continue
out.append(rel)
return out
def sha256(path):
h = hashlib.sha256()
with open(path, "rb") as fh:
for chunk in iter(lambda: fh.read(65536), b""): h.update(chunk)
return h.hexdigest()
def write_checksums(root=SKILL_DIR):
"""sha256sum-compatible CHECKSUMS.txt next to SKILL.md so drift shows in git diffs."""
lines = [f"{sha256(os.path.join(root, rel))} {rel}" for rel in shipped_files(root)]
with open(os.path.join(root, CHECKSUMS), "w", encoding="utf-8", newline="\n") as fh: fh.write("\n".join(lines) + "\n") # LF on every OS
return lines
def compare(src, dst, files):
"""Per-file status: same | differs | missing."""
rows = []
for rel in files + [CHECKSUMS]:
a, b = os.path.join(src, rel), os.path.join(dst, rel)
if not os.path.exists(b): rows.append((rel, "missing"))
elif sha256(a) != sha256(b): rows.append((rel, "differs"))
else: rows.append((rel, "same"))
return rows
def copy_tree(src, dst, files):
for rel in files + [CHECKSUMS]:
d = os.path.join(dst, rel); os.makedirs(os.path.dirname(d), exist_ok=True)
shutil.copyfile(os.path.join(src, rel), d)
def run(write=False, dests=None, src=SKILL_DIR, out=print):
files = shipped_files(src)
write_checksums(src)
dests = list(dests) if dests else destinations()
drift = 0
for d in dests:
if write: copy_tree(src, d, files)
rows = compare(src, d, files); bad = [r for r in rows if r[1] != "same"]
drift += len(bad)
out(f"{'ok ' if not bad else 'DRIFT'} {d}: {len(rows) - len(bad)}/{len(rows)} files identical" + (f"; {len(bad)} {'still ' if write else ''}differ: " + ", ".join(f"{r} ({s})" for r, s in bad[:6]) if bad else ""))
return drift
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 119k | Updated | Claude CodeCodex | Verified | Install |
| 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: 119k | Updated | Claude CodeCodex | Verified | Install |
| 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: 118k | Updated | Claude CodeCodex | Verified | Install |
| 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: 118k | Updated | Claude CodeCodex | Verified | Install |