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-costs.md
View on GitHub---
slug: cc-costs
title: Manage costs effectively
publisher: Anthropic
url: https://code.claude.com/docs/en/costs
fetchedAt: 2026-10-31
lastVerifiedAt: 2026-11-11
linkStatus: ok
finalUrl:
---
# Manage costs effectively
## Summary
- Token cost grows with context size, so keeping context small is the main lever; caching and auto-compaction help but do not replace habits.
- `/usage` shows session tokens and, on plans, a breakdown of what drives consumption with suggested fixes.
- Use `/clear` when switching to unrelated work, since stale context is resent with every message.
- Give `/compact` focus instructions, or put compaction guidance in `CLAUDE.md`, so the summary keeps what matters.
- Pick a cheaper model for most work and reserve the strongest one for hard reasoning; simple subagents can run on a small model.
- Prefer CLI tools over MCP servers where possible, and disable MCP servers you are not using.
- Hooks can pre-filter large output such as logs, and skills load only when invoked, keeping the base context lean.
- Keep `CLAUDE.md` essentials-only, under roughly 200 lines, and move workflow-specific detail into skills.
- Delegate verbose work like tests, docs fetching and log processing to subagents so only a summary returns to the main thread.
- Lower effort or thinking budget for simple tasks, write specific prompts, use plan mode, and course-correct early.
- Agent teams multiply token use per teammate, so keep them small and shut teammates down when finished.
- Long sessions, cache misses and idle scheduled tasks all quietly add usage.
## Cited quotes
- "the verbose output stays in the subagent's context while only a summary returns to your main conversation." (ctx-subagent-offload)
- "For simple subagent tasks, specify model: haiku in your subagent configuration." (ctx-custom-subagents)
- "/compact Focus on code samples and API usage tells Claude what to preserve during summarization." (ctx-compact-focus)
- "Skills load on-demand only when invoked, so moving specialized instructions into skills keeps your base context smaller." (doc-skills-on-demand)
- "You can also customize compaction behavior in your CLAUDE.md file at the root of your project" (ctx-compact-focus)
- "Aim to keep CLAUDE.md under 200 lines by including only essentials." (doc-skills-on-demand)
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 |