alluvium CLAUDE.md

alluvium CLAUDE.md is an instructions file for coding agents from Tespera/alluvium. It costs 2,410 tokens per session, scanned B, original, Apache-2.0.

A set of Claude Code instructions for Alluvium, a tool that automatically turns coding sessions into organised Obsidian notes.

In plain words
What is it for?
Use it when working on Alluvium features involving session archiving, topic pages, hooks, the knowledge model, or its Rust and Claude Code integration.
Why use it?
It gives the agent the project's rules for storing knowledge and prevents implementations from drifting from its intended design.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/tespera/alluvium/claude-md
Clone the repo
git clone --depth 1 https://github.com/Tespera/alluvium

Wrote 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.

agentmods badge for alluvium CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tespera/alluvium/claude-md.svg)](https://agentmods.dev/instructions/tespera/alluvium/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tespera/alluvium/claude-md"><img src="https://agentmods.dev/badge/instructions/tespera/alluvium/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,410 This file is loaded in full into every session.
When invoked 2,410 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.02410 $0.02410
Opus 5 $0.01205 $0.01205
Sonnet 5 $0.00482 $0.00482
Haiku 4.5 $0.00241 $0.00241

Measured 4d ago against content hash 5ce72d3cdd09, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

alluvium CLAUDE.md scanned grade B with 1 finding 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- ❌ 让用户手编辑 `~/.claude/settings.json` 注入 hook(**用 `.claude-plugin/plugin.json`**)
CLAUDE.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Alluvium · 项目宪法

你(AI)每次进入这个仓库,先读这份文件,再读 docs/LLM_WIKI_DOCTRINE.md。 后者是产品圣经(Karpathy LLM Wiki 模式的忠实落地原则),是判断"实现是否对路"的最终标尺。 任何与本文件或圣经冲突的实现都是错的——遇到分歧请向用户提问,不要自行决定推翻这里的约定

一句话

Alluvium 是一个 Claude Code session 自动归档器:每次 Claude Code 会话结束后,被动地把对话蒸馏成"精华笔记",按 Karpathy 的 LLM Wiki 模式合并进用户的 Obsidian vault。

卖点(README slogan)

You don't save your sessions. Your sessions save themselves.

跟同赛道 8 个 obsidian 类项目(claudesidian / claudian / claude-obsidian / obsidian-second-brain 等)的核心差异:

  • 别人是主动唤起(slash command / 侧边栏 / MCP 按需调用);Alluvium 是被动归档(hook 触发,用户无感)。
  • 别人多数存原始对话或简单摘要;Alluvium 蒸馏后合并到 topic 页,不留 session 日志。
  • 别人多数是 Obsidian 插件或 Claude 内嵌助手;Alluvium 是外部 Rust 二进制 + Claude Code Plugin

如果 AI 在写"侧边栏"、"slash command"、"per-session note 文件"这类东西,停下来重读本文——多半跑偏了。

知识组织模型(核心,详见 docs/KNOWLEDGE_MODEL.md

vault 内三层:

<vault>/Alluvium/
├── raw/sessions/        # 不可变原档:每次 session 一份 transcript 副本
├── wiki/
│   ├── index.md         # 主题分类 hub
│   ├── log.md           # append-only 时间线(一行一 session)
│   ├── overview.md
│   ├── concepts/        # 概念、模式、技术(topic 页)
│   ├── entities/        # 项目、工具、人、库(topic 页)
│   └── sources/         # 单 session 摘要(可选层)
└── CLAUDE.md            # vault 内的 schema 文件(注意:这个 CLAUDE.md ≠ 仓库根的这份)

核心原则:知识沉淀到 topic 页(concepts/ 和 entities/),session 不直接变成笔记。session 的最终去处是 raw/sessions/ 作为不可变原档,知识被抽出后向上汇总进 wiki。

Hook 架构(4 个,详见 docs/HOOKS.md

SessionStart  →  写 `<cache>`/sessions/<id>/resolved.json
PreCompact    →  快照当前 transcript 防 compact 后丢
Stop          →  spawn detached 子进程,hook 立即返回(不卡 Claude Code)
SessionEnd    →  清理临时文件

PreCompact 不能省——长 session 中途 compaction 会丢原始细节。 detached spawn 不能省——蒸馏要 5-30 秒,hook 必须 100ms 内返回。

硬约束(不可违反)

  1. 用户是纯 VibeCoder,不写也不读代码。任何代码层选项都要翻译成"对用户可见的影响"才呈现。
  2. prompt / config / 中间产物必须是外部文件(toml / yaml / md / json),用户能直接编辑、能用 Obsidian 打开看。
  3. 测试是用户的眼睛——功能正确性靠 cargo test 通过/失败回答。测试名要表达用户可见的断言(参考 tests/e2e_*.rs 命名)。
  4. 单二进制分发——cargo build --release 出来的二进制独立运行,不依赖 Python / Node 等环境。
  5. 保留用户手改——用户可能在 Obsidian 里手动改过任何 wiki 页。merge 时只能覆盖 Alluvium 上次写的部分,必须 diff。
  6. 自我引用屏蔽——cwd 在 Alluvium 自己开发目录的 session 不归档(避免递归)。

Read the full file on GitHub · 162 lines

Changes

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.

  1. 4d ago First seen · 162 lines · 2,410 tokens per session scan B 5ce72d3cdd09

Subscribe to this mod's changes

alluvium CLAUDE.md is an instructions file published in the GitHub repository Tespera/alluvium (1 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 2,410 tokens to every session, about $0.0120 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

pi-llm-wiki AGENTS.md

AGENTS.md instructions for zosmaai/pi-llm-wiki, covering agents.md, project, tech stack, file layout and conventions.

zosmaai/pi-llm-wiki · 594 tokens

obsidian-llm-wiki CLAUDE.md

Claude Code instructions for green-dalii/obsidian-llm-wiki, a project described as: Karpathy's LLM Wiki implementation plugin for Obsidian - turns notes and PDFs into a linked, LLM-powered knowledge base with entity pages, concept pages, graph-powered Q&A, and local-first privacy.

green-dalii/obsidian-llm-wiki · 234 tokens

obsidian-llm-wiki AGENTS.md

AGENTS.md instructions for green-dalii/obsidian-llm-wiki, covering llm wiki plugin project development standards, 🛡️ six-gate quality closure, gate 1: five-gate automated, gate 2: no side effects and gate 3: no breaking changes.

green-dalii/obsidian-llm-wiki · 7,700 tokens

wenlan CLAUDE.md

Claude Code instructions for 7xuanlu/wenlan, a project described as: Wenlan is a knowledge base for the AI-native age. Your AI agents capture what they learn, Wenlan keeps it current and distills it into source-cited wiki pages you can trust.

7xuanlu/wenlan · 99 tokens

memex-plugin CLAUDE.md

Instructions for linxule/memex-plugin, covering memex - personal knowledge base, quick start, check vault status, search for something (rrf scoring is default) and search recent docs only (7d, 2w, 3m).

linxule/memex-plugin · 2,575 tokens

llm-brain CLAUDE.md

Instructions for kimsanguine/llm-brain, covering llm-brain — claude code 운영 지침, 가드레일 (절대 위반 금지), 프라이버시 경계 (agent memory os), 명령어 and ingest.

kimsanguine/llm-brain · 3,289 tokens