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-maximizing-sessions.md
View on GitHub---
slug: cc-art-maximizing-sessions
title: Maximizing the value of your Claude Code sessions
publisher: Anthropic
url: https://claude.com/resources/articles/maximizing-the-value-of-your-claude-code-sessions
fetchedAt: 2026-11-11
lastVerifiedAt: 2026-11-11
linkStatus: ok
finalUrl:
---
# Maximizing the value of your Claude Code sessions
## Summary
- Per-task cost depends on model, input vs output tokens and prompt-cache hits; cache reads cost about a tenth of fresh input.
- Every file read and command output stays in the conversation and is re-sent on each later turn, so context size times turns drives cost.
- Switching `/model`, `/effort` or fast mode, or running `/compact`, invalidates the cache; the cheap moments are session start or right after `/clear`.
- The cache lapses after an hour on a subscription (five minutes on an API key), so compacting before a break is cheaper than after.
- Use `/rewind` instead of `/compact` to drop a few bad turns, since rewinding keeps the cached prefix.
- Run `/context` in a fresh session, keep `CLAUDE.md` specific, move workflow detail into skills and turn off unused MCP servers.
- @-mention files instead of letting Claude search, and put everyday commands with quiet flags into `CLAUDE.md`.
- `/clear` between tasks, `/compact` with focus instructions or a "Compact instructions" section, and run `/loop` from a fresh session.
- Send noisy jobs such as log digging to a subagent; repeat jobs can get their own subagent definition on a smaller model.
## Cited quotes
- "/model: every model has its own cache, so on the next turn the entire conversation gets prefilled again at full price." (ctx-model-at-start)
- "/compact before you take a break from your keyboard." (ctx-compact-before-break)
- "the cache expires after an hour on a subscription or five minutes on an API key" (ctx-compact-before-break)
- "put a "Compact instructions" section in CLAUDE.md if it's always the same thing" (ctx-compact-focus)
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 |