Knowit/claudeplus
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

Split tooling notes and pitfalls into @-imported sidecars

Browse Source 
主文件不断累积实测工具细节和踩坑记录让核心准则变难扫读;通过 Claude Code
的 @ 导入语法把这些拆到本地 note.md / debug.md, 主文件只保留指针和纲领,
后续新增工具经验或坑直接往子文件加, 主文件保持稳定。log.md 作为会话索引
由本地 SessionEnd hook 维护, 不跟随仓库同步。
This commit is contained in:
Zhang Jiahao
2026-04-21 00:50:16 +08:00
parent 04efa2d72e
commit e99b5fe482
1 changed files with 12 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
CLAUDE.md
View File

@@ -26,12 +26,7 @@ Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-s
**Workflow: Locate → Plan → Execute.** Never jump straight to edits. **Workflow: Locate → Plan → Execute.** Never jump straight to edits.
1. **Locate**: find the relevant files, functions, call sites, and tests. Quote or cite the existing code before proposing changes. If you can't locate it, say so — don't guess. 1. **Locate**: find the relevant files, functions, call sites, and tests. Quote or cite the existing code before proposing changes. If you can't locate it, say so — don't guess. Tooling details and known pitfalls live in `note.md` / `debug.md` (auto-imported below).
- For mature/unfamiliar repos, prefer structured scans:
- `repomix -o /tmp/x.xml` (or `repomix <subdir>`) — full-repo LLM pack; slice by subdir if > 100k tokens
- `eza --tree --git-ignore --level=3 .` for layout (⚠️ path arg required, omitting it silently prints nothing); `fd <pat>` for files; `rg <sym>` for call sites
- `git ls-files` when tokens are tight
- skip `broot` — interactive-only, no value in CLI/pipeline context
2. **Plan**: state the intended change in one or two sentences. List assumptions and open questions. Give a rough estimate of **token consumption** (reads + writes + tool calls) and **wall-clock time** so the user can redirect early if the scope is off. If uncertain, ask before writing code. 2. **Plan**: state the intended change in one or two sentences. List assumptions and open questions. Give a rough estimate of **token consumption** (reads + writes + tool calls) and **wall-clock time** so the user can redirect early if the scope is off. If uncertain, ask before writing code.
3. **Execute**: make the minimal edit that matches the plan. Deviations require a new plan, not silent improvisation. 3. **Execute**: make the minimal edit that matches the plan. Deviations require a new plan, not silent improvisation.
@@ -77,6 +72,17 @@ For multi-step tasks, state a brief plan:
Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification. Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
## 5. Extended references (auto-imported)
These files expand into context at session start:
- Practice notes: @~/.claude/note.md
- Debug pitfalls: @~/.claude/debug.md
Not auto-imported (read on demand):
- Session log: `~/.claude/log.md` — appended by SessionEnd hook, grows unboundedly so kept out of context to save tokens
--- ---
**These guidelines are working if:** fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes. **These guidelines are working if:** fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.