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/cursor-agent-best-practices.md
View on GitHub---
slug: cursor-agent-best-practices
title: Best practices for coding with agents
publisher: Cursor
url: https://cursor.com/blog/agent-best-practices
fetchedAt: 2026-10-31
lastVerifiedAt: 2026-11-11
linkStatus: ok
finalUrl:
---
# Best practices for coding with agents
## Summary
- Plan before coding: use Plan Mode so the agent researches, asks questions and drafts a plan you can edit and save.
- If results drift from intent, revert and sharpen the plan instead of stacking follow-up prompts.
- Let the agent search for context; tag files only when you already know the exact one.
- Start a fresh conversation when the task changes or the agent repeats mistakes, and reference past work with `@Chats`.
- Keep rules short, listing key commands, style patterns and example files; add one only after the same mistake recurs.
- Commit rules to git so the team shares them, and package repeatable workflows as commands, skills or hooks.
- Give the agent verifiable goals such as tests; test-driven work with failing tests first lets it iterate to success.
- Review diffs carefully, use built-in review passes, and stop the agent early when it heads the wrong way.
- Run parallel agents in separate worktrees or compare several models on the same prompt.
- Use images for design-to-code, and hand background jobs to cloud agents.
## Cited quotes
- "Start simple. Add rules only when you notice the agent making the same mistake repeatedly." (doc-update-on-repeat)
- "The most impactful change you can make is planning before coding." (plan-mode-first)
- "Tests allow the agent to make changes, evaluate results, and incrementally improve until it succeeds." (verify-runnable-checks)
- "Revert the changes, refine the plan to be more specific about what you need, and run it again." (verify-revert-retry)
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 |