Skip to content

Adonis0123/adonis-skills / skills/agent-practice-audit

agent-practice-audit

Flagged

Score how someone uses coding agents (Claude Code, Codex, Grok and WorkBuddy session logs, instruction files, hooks, permissions, Codex config) against practices quoted from official vendor docs, and write a local HTML report with coverage, trend and suggestions; also refresh or verify that practice list from official docs with multi-model consensus. Use when the user asks how far their agent usage is from official practice, wants an agent usage check-up or grade, or wants the practice list refreshed, its links checked, or either run on a schedule. Chinese triggers: Agent 用法体检、对照官方最佳实践、我的 agent 用得对不对、给 agent 用法打分、更新最佳实践清单. Not for whether a tool, MCP or skill is worth keeping (dev-environment-roi-audit), for writing or reviewing one CLAUDE.md or AGENTS.md, for general best-practice questions, or for Cursor or Gemini CLI logs, which it does not read. Never edits the user's config.

FileKindSize
SKILL.mdskill md18.3 KB
assets/default-config.jsonconfig352 B
assets/img/hero.webpbinary106.5 KB
assets/img/nika-wordmark-white.svgother490 B
assets/img/nika-wordmark.svgother490 B
assets/report-template.htmlother41.2 KB
evals/evals.jsonconfig844 B
evals/trigger-eval-set.jsonconfig1.6 KB
references/audit-files.mdmarkdown32.2 KB
references/changelog.mdmarkdown7.2 KB
references/practices.jsonconfig37.3 KB
references/scheduling.mdmarkdown11.9 KB
references/sources.mdmarkdown6.5 KB
references/sources/cc-art-loops.mdmarkdown1.7 KB
references/sources/cc-art-maximizing-sessions.mdmarkdown1.9 KB
references/sources/cc-art-opus-5-5-context.mdmarkdown1.4 KB
references/sources/cc-art-sdlc-playbook.mdmarkdown1.9 KB
references/sources/cc-art-steering.mdmarkdown1.9 KB
references/sources/cc-art-verification-loops.mdmarkdown1.6 KB
references/sources/cc-best-practices.mdmarkdown3.0 KB
references/sources/cc-common-workflows.mdmarkdown1.7 KB
references/sources/cc-costs.mdmarkdown2.3 KB
references/sources/cc-memory.mdmarkdown1.7 KB
references/sources/codex-agents-md.mdmarkdown1.5 KB
references/sources/codex-best-practices.mdmarkdown2.6 KB
references/sources/codex-non-interactive.mdmarkdown1.3 KB
references/sources/codex-sandboxing.mdmarkdown1.4 KB
references/sources/cursor-agent-best-practices.mdmarkdown1.8 KB
references/verify-prompt.mdmarkdown4.6 KB
scripts/aggregate.pyscript22.3 KB
scripts/audit_common.pyscript8.6 KB
scripts/build_report.pyscript30.8 KB
scripts/check_practices.pyscript24.8 KB
scripts/config_scan.pyscript28.3 KB
scripts/consensus.pyscript38.1 KB
scripts/digests.pyscript10.2 KB
scripts/export_metrics.pyscript10.3 KB
scripts/extract.pyscript42.5 KB
scripts/prejudge.pyscript41.8 KB
scripts/run_audit.pyscript3.8 KB
scripts/safe_output.pyscript2.0 KB
scripts/test_agent_practice_audit.pyscript81.1 KB
scripts/test_consensus_run.pyscript26.9 KB
scripts/test_measurement.pyscript68.7 KB
scripts/test_prejudge.pyscript24.2 KB

scripts/run_audit.py

View on GitHub
#!/usr/bin/env python3
"""Run the audit data steps in one call: extract -> aggregate -> config_scan -> prejudge.

Usage: run_audit.py [--days N] [--repo DIR ...] [--run DIR]

RUN defaults to $AGENT_PRACTICE_AUDIT_DIR/reports/YYYY-MM-DD (base default
~/.local/share/agent-practice-audit). Work files go to RUN/work. Prints the
extract host lines and the judge-input.json path. Exits 3 when the window holds
no human sessions, naming the roots that were searched.
"""

from __future__ import annotations

import argparse
import datetime
import json
import os
import subprocess
import sys
import time

HERE = os.path.dirname(os.path.abspath(__file__))
sys.path.insert(0, HERE)
from safe_output import UnsafeOutput, safe_output_path  # noqa: E402

NO_SESSIONS = 3


def default_run() -> str:
    base = os.environ.get("AGENT_PRACTICE_AUDIT_DIR") or os.path.join("~", ".local", "share", "agent-practice-audit")
    return os.path.join(os.path.expanduser(base), "reports", datetime.date.today().isoformat())


def step(name: str, args: list[str], echo: bool = False) -> None:
    """Run one sibling script; stop the whole run with its stderr when it fails."""
    p = subprocess.run([sys.executable, os.path.join(HERE, name), *args], capture_output=True, text=True)
    if echo and p.stdout:
        sys.stdout.write(p.stdout)
    if p.returncode:
        sys.stderr.write(p.stderr or p.stdout)
        raise SystemExit(f"error: {name} exited {p.returncode}")


def searched_roots() -> list[str]:
    """Glob roots extract.py used, in `~/` form, for the no-sessions message."""
    import importlib.util
    spec = importlib.util.spec_from_file_location("extract", os.path.join(HERE, "extract.py"))
    ex = importlib.util.module_from_spec(spec)
    spec.loader.exec_module(ex)
    home = os.path.expanduser("~")
    cfg = ex.load_config()
    return [f"{h}: " + ", ".join(p.replace(home, "~", 1) for p in ex.globs_for(h, cfg)) for h in ex.HOSTS]


def main(argv=None) -> int:
    ap = argparse.ArgumentParser(description=__doc__.splitlines()[0])
    ap.add_argument("--days", type=int, default=60)
    ap.add_argument("--repo", action="append", default=[], help="extra repository to scan (repeatable)")
    ap.add_argument("--run", help="run directory (default $AGENT_PRACTICE_AUDIT_DIR/reports/YYYY-MM-DD)")
    a = ap.parse_args(argv)
    try:
        run = safe_output_path(a.run or default_run())
    except UnsafeOutput as e:
        print(f"error: {e}", file=sys.stderr)
        return 2
    work = os.path.join(run, "work")
    os.makedirs(work, exist_ok=True)
    sessions, summary = os.path.join(work, "sessions.jsonl"), os.path.join(work, "summary.json")
    config, judge = os.path.join(work, "config-scan.json"), os.path.join(work, "judge-input.json")
    t0 = time.time()

    step("extract.py", [sessions, "--days", str(a.days)], echo=True)
    step("aggregate.py", [sessions, "-o", summary])
    with open(summary, encoding="utf-8") as f:
        hosts = json.load(f).get("hosts") or {}
    if not hosts:
        print(f"error: no human sessions with prompts in the last {a.days} days. Searched:", file=sys.stderr)
        for line in searched_roots():
            print(f"  {line}", file=sys.stderr)
        print(f"Try a longer window (--days {a.days * 2}) or add roots via AGENT_PRACTICE_AUDIT_<HOST>_GLOBS "
              "or extraRoots in config.json. No report was built.", file=sys.stderr)
        return NO_SESSIONS

    scan_args = ["--summary", summary, "-o", config]
    for r in a.repo:
        scan_args += ["--repo", r]
    step("config_scan.py", scan_args)
    step("prejudge.py", ["--summary", summary, "--config", config, "--days", str(a.days), "-o", judge])
    print(f"run: {run}")
    print(f"judge-input: {judge} ({os.path.getsize(judge)} bytes, {time.time() - t0:.1f}s total)")
    return 0


if __name__ == "__main__":
    sys.exit(main())
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall