Borrowing it
Nothing to install: this file belongs to tznthou/ccRecall. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tznthou/ccRecall/main/CLAUDE.mdgit clone --depth 1 https://github.com/tznthou/ccRecallWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/tznthou/ccrecall/claude-md)<a href="https://agentmods.dev/instructions/tznthou/ccrecall/claude-md"><img src="https://agentmods.dev/badge/instructions/tznthou/ccrecall/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/tznthou/ccrecall/claude-md"><img src="https://agentmods.dev/badge/instructions/tznthou/ccrecall/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01118 | $0.01118 |
| Opus 5.5 | $0.00447 | $0.00447 |
| Sonnet 5.5 | $0.00224 | $0.00224 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
ccRecall CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ccRecall — AI Memory Service for Claude Code
ccRewind 的姐妹作。ccRewind 做「考古」（事後看 session 發生了什麼），ccRecall 做「記憶」（讓 AI 在未來 session 中自動記住過去的經驗）。
定位
本地背景服務，讀取 Claude Code 對話歷史，讓 AI 在未來 session 中按需記憶——不全部載入，只注入最相關的片段（<300 tokens）。
核心模組從 ccRewind 抽取（parser, scanner, summarizer, database, indexer），新增記憶層、HTTP API、元認知索引。
指令
- dev:
pnpm dev - build:
pnpm build - test:
pnpm vitest run - lint:
pnpm eslint . --fix - start:
pnpm start
技術約束
- Runtime: Node.js + TypeScript
- DB: better-sqlite3 + FTS5（同步 API，零外部依賴）
- HTTP: 輕量 HTTP server（localhost only）
- 摘要引擎: 規則式（零 API 成本），不依賴 LLM
- 純唯讀應用——絕對不修改
~/.claude/下的任何檔案 - JSONL parser 採寬容模式：未知結構保留 raw JSON，不中斷解析
- 不用 Docker、不用 Electron、不用向量資料庫
架構
三條讀取路徑 + 一條寫入路徑，共用同一個 SQLite 檔（MCP 走 WAL 直接開檔，不經 HTTP）。
讀（注入）
SessionStart hook ──HTTP──→ /memory/startup ┐
UserPromptSubmit hook ──HTTP──→ /memory/prompt ├─→ ccRecall daemon :7749 ─┐
MCP recall_query/context ─────── WAL 直接開檔 ─────────────────────────────┐ │
↓ ↓
寫（產生記憶） SQLite + FTS5 ├── memories
ccrecall-extract wrapper → claude -p → MCP recall_save ──→ ├── memory_topics
手動 recall_save ────────────────────────────────→ ├── knowledge_map
├── injection_log
索引（唯讀來源） └── sessions/messages
~/.claude/**/*.jsonl → watcher → scanner → parser → summarizer → indexer ↑
⚠️ 摘要引擎（summarizer）是規則式零成本，但記憶抽取（extraction）走 LLM（claude -p，
模型與 effort 以 scripts/post-session-extract.sh 為準）——兩件事，別混為一談。SessionEnd
hook 只標記結束，不抽取；抽取只在 ccrecall-extract（zsh alias ccdm）收尾時跑。
測試誠信
- 測試紅了先修程式，禁止為通過測試而改斷言
- 先寫測試、後寫實作
- 測試不碰生產資料：使用 mkdtemp 隔離，不操作真實
~/.claude/
相關專案
- ccRewind:
/Users/tznthou/Documents/ccRwind/（考古 GUI，核心模組來源）
參考文件（需要時再讀）
- 架構設計:
.claude/pi-research/ccrewind-memory-service-architecture.md - AI 記憶全景:
.claude/pi-research/ai-memory-systems-landscape.md - 元認知設計:
.claude/pi-research/ai-long-term-memory-design.md - Obsidian 記憶研究:
.claude/pi-research/obsidian-ai-deep-memory.md - Hooks 注入可行性:
.claude/pi-research/hooks-context-injection-feasibility.md - LLM Wiki 範式分析:
.claude/pi-research/llm-wiki-karpathy-analysis.md
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago Changed · -9 lines · -105 tokens per session d520f72ed035
- 1mo ago Changed · +16 lines · +275 tokens per session ae43b6f6a95e
- 1mo ago First seen · 75 lines · 948 tokens per session scan A 93b5c6aaad70
ccRecall CLAUDE.md is an instructions file published in the GitHub repository tznthou/ccRecall (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,118 tokens to every session, about $0.0045 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.