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-non-interactive.md
View on GitHub---
slug: codex-non-interactive
title: Non-interactive mode
publisher: OpenAI
url: https://learn.chatgpt.com/docs/non-interactive-mode
fetchedAt: 2026-10-31
lastVerifiedAt: 2026-11-11
linkStatus: ok
finalUrl:
---
# Non-interactive mode
## Summary
- `codex exec` runs Codex in scripts and CI without the interactive interface.
- Progress goes to stderr and only the final message goes to stdout, so output is easy to pipe or redirect.
- Piped stdin is added as context when a prompt is also supplied, and `--ephemeral` avoids saving session files.
- Runs default to a read-only sandbox; writing needs workspace-write, and full access belongs only in controlled environments.
- `--json` emits a JSON Lines event stream, `-o` saves only the final message, and `--output-schema` requests a response matching a schema.
- Authenticate with an API key scoped to the single invocation, and keep keys away from steps that run untrusted repository code.
- The `resume` subcommand continues a prior session, and runs expect a Git repository unless the check is skipped.
- Examples include a CI workflow that proposes fixes after failed builds and patterns for piping command output into `codex exec`.
## Cited quotes
- "Use danger-full-access only in a controlled environment" (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 |