Adonis0123/adonis-skills / skills/agent-practice-audit
agent-practice-audit
FlaggedScore 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.
references/sources/codex-sandboxing.md
View on GitHub---
slug: codex-sandboxing
title: Sandbox
publisher: OpenAI
url: https://learn.chatgpt.com/docs/sandboxing.md
fetchedAt: 2026-10-31
lastVerifiedAt: 2026-11-11
linkStatus: ok
finalUrl:
---
# Sandbox
## Summary
- The sandbox sets technical limits on what the agent and the commands it spawns can do during local runs.
- Sandbox and approval policy are separate controls: one sets boundaries, the other decides when to stop and ask.
- Enforcement is OS-native: Seatbelt on macOS, a native sandbox or WSL2 on Windows, and `bubblewrap` on Linux.
- Three modes exist: read-only, workspace-write (the usual default) and danger-full-access with no filesystem or network limits.
- Approval policies are on-request or never; the older untrusted option is retired.
- Approvals can be reviewed by the user or, for eligible requests, an automatic reviewer agent; the sandbox boundary stays the same.
- Full access means danger-full-access plus never asking; the lower-risk preset pairs workspace-write with on-request approvals.
- Extra writable roots and command-prefix rules offer narrower exceptions than turning the sandbox off.
- Some Linux distributions need an AppArmor profile for `bubblewrap`; disabling the restriction globally is a weaker fallback.
## Cited quotes
- "the lower-risk local automation preset is sandbox_mode = "workspace-write" together with approval_policy = "on-request"" (safe-low-risk-preset)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 471k | Updated | Claude CodeCodex | Verified | Install |
| 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: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |