98% of Battle Drones Was Written by Claude: I Audited 334 Commits With 140 Lines of Python

#!/usr/bin/env python3 """agentaudit.py: how much of a git repo did coding agents write? Usage: python3 agentaudit.py [REPO] [--days 14] [--top 8] (stdlib only) """ import argparse, collections, datetime as dt, re, subprocess # One regex per agent, matched against "author / committer / full message". AGENTS = { "Claude": r"noreply@anthropic\.com|co-authored-by:[^\n]*claude|claude-session:" r"|claude\.ai/code/session|generated with \[claude code\]", "Codex": r"co-authored-by:[^\n]*codex|chatgpt-codex-connector|codex@openai\.com", "Copilot": r"copilot-swe-agent|\+copilot@users\.noreply|co-authored-by:[^\n]*copilot", "Cursor": r"cursoragent@cursor\.com|co-authored-by:[^\n]*cursor", "Devin": r"devin-ai-integration", "Aider": r"\(aider\)|co-authored-by:[^\n]*aider", } AGENTS = {k: re.compile(v, re.I | re.M) for k, v in AGENTS.items()} BOT = re.compile(r"\[bot\]|actions@users\.noreply|github-actions", re.I) # CI, not agents FIX = re.compile(r"^(revert|fixup!|hotfix)|\b(fix(es|ed)?|bug|regression|broke|broken|oops)\b", re.I) TRAILER = re.compile(r"^co-authored-by:\s*([^<\n]+?)\s*<", re.I | re.M) # Generated files inflate line counts; skip them (override with --skip). SKIP = r"(^|/)(dist|build|vendor|node_modules|docs/assets)/|\.lock$|-lock\.json$|\.min\.|\.map$" FMT = "%x00%H%x1f%an <%ae>%x1f%cn <%ce>%x1f%at%x1f%P%x1f%B%x1e" def who(author, committer, msg): text = f"{author}\n{committer}\n{msg}" return next((name for name, rx in AGENTS.items() if rx.search(text)), None) def audit(repo, days, skip_rx): skip_rx = re.compile(skip_rx) out = subprocess.run(["git", "-C", repo, "log", "--reverse", "-p", "-M", "--unified=0", "--no-color", "--format=" + FMT], capture_output=True, text=True, errors="replace", check=True).stdout window = days * 86400 s = collections.defaultdict(collections.Counter) # stat name -> {"agent"/"human": n}  per_agent, models = collections.Counter(), collections.Counter() files, day = collections.defaultdict(collections.Counter), collections.defaultdict(collections.Counter) added = collections.defaultdict(lambda: collections.defaultdict(collections.deque)) last_touch = {} # path -> (ts, cls)  for chunk in out.split("\x00")[1:]: head, patch = chunk.split("\x1e", 1) sha, author, committer, ts, parents, msg = head.split("\x1f") ts = int(ts) if len(parents.split()) > 1: s["merges"]["all"] += 1 continue agent = who(author, committer, msg) if not agent and BOT.search(author): s["merges"]["bots"] += 1 continue cls = "agent" if agent else "human" if agent: per_agent[agent] += 1 models.update(t for t in TRAILER.findall(msg) if AGENTS[agent].search(f"co-authored-by: {t}")) s["commits"][cls] += 1 if not agent and re.search(r"\(#\d+\)$", msg.split("\n", 1)[0].strip()): s["squash"]["human"] += 1 # squash-merged PR: author unknown  d = dt.datetime.fromtimestamp(ts, dt.timezone.utc).strftime("%Y-%m-%d") day[d][cls] += 1 path, in_hunk, skip, touched = None, False, False, set() for line in patch.split("\n"): if line.startswith("diff --git "): m = re.match(r"diff --git a/(.*) b/(.*)", line) old, path = (m.group(1), m.group(2)) if m else (None, line) if old and old != path and old in added: # follow renames  added[path] = added.pop(old) skip = bool(skip_rx.search(path)) if not skip: touched.add(path) in_hunk = False elif line.startswith("@@"): in_hunk = not skip elif in_hunk and line[:1] in ("+", "-"): content = line[1:].strip() s["lines"][cls] += 1 files[path][cls] += 1 day[d][cls + "_lines"] += 1 if line[0] == "+": s["added"][cls] += 1 if len(content) > 2: # skip "}", "", ");"  added[path][content].append((ts, cls)) elif added[path][content]: t0, c0 = added[path][content].popleft() # oldest matching add  if ts - t0 <= window: s["churn"][c0] += 1 if FIX.search(msg.split("\n", 1)[0]): s["fixes"][cls] += 1 hit = {last_touch[p][1] for p in touched if p in last_touch and ts - last_touch[p][0] <= window} s["fix_after"].update(hit) for p in touched: last_touch[p] = (ts, cls) return s, per_agent, models, files, day def pct(a, b): return f"{100 * a / b:5.1f}%" if b else " n/a" def report(repo, days, top, skip_rx): s, per_agent, models, files, day = audit(repo, days, skip_rx) c, l = s["commits"], s["lines"] nc, nl = sum(c.values()), sum(l.values()) print(f"repo: {repo} window: {days} days merges skipped: {s['merges']['all']} bot commits skipped: {s['merges']['bots']}") print(f"commits agent {c['agent']:>6} {pct(c['agent'], nc)} human {c['human']:>6} {pct(c['human'], nc)}") print(f" human commits that look like squash-merged PRs (true author unknown): " f"{s['squash']['human']}") print(f"lines agent {l['agent']:>6} {pct(l['agent'], nl)} human {l['human']:>6} {pct(l['human'], nl)}") print("agents " + ", ".join(f"{k} {v}" for k, v in per_agent.most_common())) print("models " + ", ".join(f"{k} {v}" for k, v in models.most_common(5))) for cls in ("agent", "human"): print(f"churn {cls}: {s['churn'][cls]} of {s['added'][cls]} added lines deleted within " f"{days}d ({pct(s['churn'][cls], s['added'][cls]).strip()})") print(f"fixes fix/revert commits: {sum(s['fixes'].values())} (by agent {s['fixes']['agent']}, " f"by human {s['fixes']['human']})") for cls in ("agent", "human"): print(f" touching files last changed by {cls} work <= {days}d earlier: " f"{s['fix_after'][cls]} ({s['fix_after'][cls] / max(c[cls], 1) * 100:.1f} per 100 {cls} commits)") print(f"\ntop {top} files by agent-changed lines:") for p, n in sorted(files.items(), key=lambda kv: -kv[1]["agent"])[:top]: print(f" {n['agent']:>6} {pct(n['agent'], n['agent'] + n['human'])} agent {p}") print("\nday commits A/H lines A/H agent share of lines") for d in sorted(day): n = day[d] share = n["agent_lines"] / max(n["agent_lines"] + n["human_lines"], 1) print(f"{d} {n['agent']:>4}/{n['human']:<4} {n['agent_lines']:>7}/{n['human_lines']:<6} " f"{'#' * round(share * 20):<20}") if __name__ == "__main__": ap = argparse.ArgumentParser(description=__doc__) ap.add_argument("repo", nargs="?", default=".") ap.add_argument("--days", type=int, default=Source：https://dev.to/neeraj_sharma_757fbb49aa7/98-of-battle-drones-was-written-by-claude-i-audited-334-commits-with-140-lines-of-python-2jmf
My favorites