anamnesis CLAUDE.md

anamnesis CLAUDE.md is an instructions file for Claude Code from oscardvs/anamnesis. It costs 838 tokens per session, scanned A, original, Apache-2.0.

Repository-specific instructions for Claude Code, an AI coding assistant, when working on the Anamnesis project. Anamnesis stores searchable memory in Markdown files, indexes it locally with SQLite, syncs it between a user's machines, and provides a dashboard.

In plain words
What is it for?
Use it when modifying, reviewing, or navigating the Anamnesis repository. It helps the assistant understand where memory, indexing, syncing, the server, and dashboard fit together.
Why use it?
It gives the coding assistant the project's design decisions, file layout, and working rules so changes stay consistent. It also prevents repeatedly debating choices that the project has already settled.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

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/oscardvs/anamnesis/claude-md
Clone the repo
git clone --depth 1 https://github.com/oscardvs/anamnesis

Made for: Claude Code.

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 anamnesis CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/oscardvs/anamnesis/claude-md.svg)](https://agentmods.dev/instructions/oscardvs/anamnesis/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/oscardvs/anamnesis/claude-md"><img src="https://agentmods.dev/badge/instructions/oscardvs/anamnesis/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 838 This file is loaded in full into every session.
When invoked 838 The same file — it is already loaded in full.
Security scan A 0 findings. 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 5.1 $0.00838 $0.00838
Opus 5 $0.00419 $0.00419
Sonnet 5 $0.00168 $0.00168
Haiku 4.5 $0.00084 $0.00084

Measured 5d ago against content hash 7100f7723f54, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

anamnesis 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.

CLAUDE.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - working in the Anamnesis repo

Guidance for Claude Code (and contributors' agents) working in this repository.

What this is

Anamnesis is a cross-machine, file-first memory layer for Claude Code. Memory is stored as markdown (source of truth) + a SQLite FTS5 index (rebuilt locally), synced across a user's own machines via git over a Tailscale mesh, exposed to Claude Code via an MCP server, and browsed through a git-like Next.js dashboard. Open-core: the local-first core is Apache-2.0.

Architecture decisions (do not relitigate without evidence)

  • File-first, not graph. Markdown is the source of truth. We do not build a knowledge-graph memory or a custom context compressor for v1 - the research shows files + keyword search are competitive and graphs add cost without proportional benefit. Revisit only if recall quality on real usage demonstrably suffers.
  • SQLite is first-class, not an afterthought. FTS5 for keyword/BM25 recall; use WAL mode so multiple concurrent Claude Code sessions don't hit file-locking conflicts. Add sqlite-vec vectors only when keyword search measurably fails on paraphrase queries.
  • Never sync the raw DB file over cloud folders (the claude-brain corruption lesson). Sync markdown via git; rebuild the index locally on each machine.
  • Sync evolution: git-as-sync for the MVP → Turso/libSQL embedded replicas when multi-user lands → CRDTs only if true concurrent multi-writer editing appears.
  • The reflection/compression model is swappable. Never hardcode it - the price/quality frontier moves weekly (see docs/research/model-landscape.md, local-only).

Repository layout

  • server/ - Python MCP server (FastMCP). Package source in server/src/anamnesis/, tests in server/tests/.
  • dashboard/ - Next.js App Router dashboard (the memory GUI).
  • scripts/ - helper scripts.
  • docs/ - PRIVATE, git-ignored, local-only. Roadmap, architecture, business case, market analysis, and research live here. They are the source of truth for why and what next - read them locally before planning work. Never commit anything under docs/.

Read the full file on GitHub · 60 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. 5d ago First seen · 60 lines · 838 tokens per session scan A 7100f7723f54

Subscribe to this mod's changes

anamnesis CLAUDE.md is an instructions file published in the GitHub repository oscardvs/anamnesis (0 stars, last pushed 4d ago), licensed Apache-2.0. It adds 838 tokens to every session, about $0.0042 per session on Opus 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.