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-opus-5-5-context.md
View on GitHub---
slug: cc-art-opus-5-5-context
title: Coding sessions are longer and use more context. Claude Opus 5.5 is built with that in mind.
publisher: Anthropic
url: https://claude.com/resources/articles/claude-opus-5-5-built-for-coding-sessions-that-use-more-context
fetchedAt: 2026-11-11
lastVerifiedAt: 2026-11-11
linkStatus: ok
finalUrl:
---
# Coding sessions are longer and use more context. Claude Opus 5.5 is built with that in mind.
## Summary
- Opus 5.5 is estimated at about 40% cheaper than Opus 5 for typical token-billed workloads, with cached reads cut most.
- Aggregate Claude Code data from March to September 2026 shows longer runs per prompt, fewer interruptions and 2.6x more context per request.
- Because most cost is now re-read context, cache efficiency matters more than before.
- Claude Code changes cut cache-missing input by over half; newer models keep the cache when effort changes mid-session.
- API and cloud users can set a one-hour cache lifetime, and forked subagents reuse the parent cache.
- Opus 5.5 may need fewer turns on open-ended tasks, though well-scoped tasks take about the same number.
- Advice: check cached share with `/usage`, pick the model at session start, compact before stepping away, and use the one-hour cache on API keys.
## Cited quotes
- "Pick your model at the start of a session rather than switching midway" (ctx-model-at-start)
- "Compact before you step away rather than after" (ctx-compact-before-break)
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 |