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.
npx agentmods add instructions/oscardvs/anamnesis/claude-mdgit clone --depth 1 https://github.com/oscardvs/anamnesisWrote 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/oscardvs/anamnesis/claude-md)<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>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 | $0.00838 | $0.00838 |
| Opus 5 | $0.00419 | $0.00419 |
| Sonnet 5 | $0.00168 | $0.00168 |
| Haiku 4.5 | $0.00084 | $0.00084 |
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.
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-vecvectors 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 inserver/src/anamnesis/, tests inserver/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 underdocs/.
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 First seen · 60 lines · 838 tokens per session scan A 7100f7723f54
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.
Other instructions, from other repositories
plur CLAUDE.md
Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
engraphis AGENTS.md
AGENTS.md instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, internal subagent delegation, 0. read this first — two architectures live in one package, 1. commands and ── unified dashboard + memory inspector ──.
brigade AGENTS.md
AGENTS.md instructions for escoffier-labs/brigade, covering agents.md, definition of done, rules, orientation and memory handoff.
Waggle-mcp AGENTS.md
AGENTS.md instructions for Abhigyan-Shekhar/Waggle-mcp, covering repository agent rules, custom rules and waggle automatic memory.
kb AGENTS.md
AGENTS.md instructions for hraness/kb, a project described as: A knowledge base for coding agents, built from Markdown, backlinks, semantic search, and Git context.
Agent-Memory-Bridge AGENTS.md
Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.