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-memory.md
View on GitHub---
slug: cc-memory
title: How Claude remembers your project
publisher: Anthropic
url: https://code.claude.com/docs/en/memory
fetchedAt: 2026-10-31
lastVerifiedAt: 2026-11-11
linkStatus: ok
finalUrl:
---
# How Claude remembers your project
## Summary
- Each session starts with a fresh context; `CLAUDE.md` files you write and auto memory notes Claude writes carry knowledge across sessions.
- Both memory systems are context, not enforcement; to block an action reliably, use a hook instead of an instruction.
- Files can live at project, user or organization scope, and a gitignored `CLAUDE.local.md` holds personal per-project preferences.
- Aim for under about 200 lines per `CLAUDE.md`; longer files cost context and lower adherence.
- Instructions should be specific and concise, and contradictory entries across files should be reviewed and removed because Claude may pick one arbitrarily.
- `CLAUDE.md` can import other files with `@path` syntax; imports outside the working directory prompt an approval step.
- Files above the working directory load at launch, while subdirectory files load on demand when Claude touches that directory.
- `.claude/rules/` splits instructions into topic files, and rules can be scoped to file paths so they load only when relevant.
- Claude Code can read a repository `AGENTS.md` in place of or alongside `CLAUDE.md`, which helps share one file across tools.
- Auto memory is per repository, shared across worktrees, and loads only the first 200 lines or 25KB each session.
- `/memory` lets you view and edit what is loaded, and the page has troubleshooting for ignored or oversized instructions.
## Cited quotes
- "target under 200 lines per CLAUDE.md file. Longer files consume more context and reduce adherence." (doc-short-instructions)
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 |