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-best-practices.md
View on GitHub---
slug: codex-best-practices
title: Best practices
publisher: OpenAI
url: https://learn.chatgpt.com/guides/best-practices
fetchedAt: 2026-10-31
lastVerifiedAt: 2026-11-11
linkStatus: ok
finalUrl:
---
# Best practices
## Summary
- Each prompt should state the goal, relevant context, constraints and what done looks like.
- Pick a reasoning effort that matches the task, lower for scoped work and higher for complex or agentic jobs.
- Use Plan mode or ask Codex to interview you before ambiguous or large tasks.
- Keep durable repo guidance in a short, accurate `AGENTS.md`, including build, test and lint commands, and revise it when mistakes repeat.
- Configure behavior at personal, repository and one-off levels so surfaces stay consistent.
- Keep approvals and sandbox tight by default; do not grant full computer access before the workflow is understood.
- Ask Codex to write tests, run checks and review its own diff before you accept changes; `/review` helps make review consistent.
- Use MCP for external context that changes often, and package repeated workflows as narrowly scoped skills.
- Schedule recurring tasks only after the manual workflow is reliable.
- Keep one chat per coherent unit of work, and fork or compact when context grows; use Git worktrees for concurrent tasks on the same files.
## Cited quotes
- "Keep one chat per coherent unit of work." (ctx-clear-between-tasks)
- "Giving Codex full permission to your computer before you understand the workflow" (safe-low-risk-preset)
- "Keep approval and sandboxing tight by default, then loosen permissions only for trusted repos or specific workflows once the need is clear." (safe-low-risk-preset)
- "A short, accurate AGENTS.md is more useful than a long file full of vague rules." (doc-short-instructions)
- "Build, test, and lint commands" (doc-test-commands)
- "When Codex makes the same mistake twice, ask it for a retrospective and update AGENTS.md." (doc-update-on-repeat)
- "Plan mode lets Codex gather context, ask clarifying questions, and build a stronger plan before implementation." (plan-mode-first)
- "If the task is complex, ambiguous, or hard to describe well, ask Codex to plan before it starts coding." (plan-mode-first)
- "Done when: What should be true before the task is complete, such as tests passing, behavior changing, or a bug no longer reproducing?" (plan-done-when)
- "Ask it to create tests when needed, run the relevant checks, confirm the result, and review the work before you accept it." (verify-runnable-checks)
- "Running live tasks on the same files without using Git worktrees" (auto-worktrees)
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 |