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/cc-art-loops.md
View on GitHub---
slug: cc-art-loops
title: Loop engineering: Getting started with loops
publisher: Anthropic
url: https://claude.com/resources/articles/getting-started-with-loops
fetchedAt: 2026-11-11
lastVerifiedAt: 2026-11-11
linkStatus: ok
finalUrl:
---
# Loop engineering: Getting started with loops
## Summary
- Defines a loop as an agent repeating cycles of work until a stop condition is met, and advises starting with the simplest loop.
- Turn-based loops are ordinary prompts; encoding manual checks as a `SKILL.md` lets Claude verify more of its own work.
- Goal-based loops (`/goal`) need verifiable exit criteria and an explicit turn cap.
- Time-based loops (`/loop`, `/schedule`) suit recurring work or polling external systems; match the interval to how often things change.
- Proactive loops combine schedules, goals, workflows and auto mode for recurring well-defined streams like triage.
- Quality depends on a clean codebase, self-verification via skills, reachable docs and a second agent with fresh context for review.
- When one result misses the bar, encode the fix into the system instead of only patching that case.
- Control tokens with the right primitive and model, clear success and stop criteria, small pilots, scripts for deterministic steps and `/usage`.
## Cited quotes
- "Use a second agent for code reviews: A reviewer with fresh context is less biased and not influenced by the main agent’s reasoning." (verify-fresh-context-review)
- "You can improve the verification step by encoding your manual steps as a SKILL.md so Claude can check more of its own work, end-to-end." (verify-checks-as-skills)
- "Define clear success and stop criteria: Be specific about what done looks like so Claude can arrive at the solution sooner" (plan-done-when)
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: 472k | 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: 472k | 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: 472k | 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 |