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/edgecaser/memsync/claude-mdgit clone --depth 1 https://github.com/EdgeCaser/memsyncWhat 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 | $0.00894 | $0.00894 |
| Opus 5 | $0.00447 | $0.00447 |
| Sonnet 5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
memsync 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 yesterday.
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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memsync — Project Context for Claude Code
You are building memsync, a cross-platform CLI tool that maintains a global identity-layer memory file for Claude Code users, synced across machines via cloud storage they already have (OneDrive, iCloud Drive, Google Drive).
This document is your entry point. Read all linked documents before writing any code.
Document map
| File | What it contains |
|---|---|
CLAUDE.md |
This file — start here |
ARCHITECTURE.md |
Full system design, module map, data flow |
PROVIDERS.md |
Provider plugin system — BaseProvider ABC, all three implementations |
CONFIG.md |
Config file design, schema, platform paths |
COMMANDS.md |
Every CLI command — args, behavior, edge cases |
EXISTING_CODE.md |
Working prototype code — use this as the base, not a reference |
PITFALLS.md |
Known issues, trust boundaries, things that have already gone wrong |
REPO.md |
Repository structure, CI, PyPI, GitHub conventions |
STYLE.md |
Code style, naming conventions, what good looks like here |
Read them in this order:
- ARCHITECTURE.md — understand the shape of the system
- EXISTING_CODE.md — understand what already works
- PROVIDERS.md — the most important new piece
- CONFIG.md — feeds into everything
- PITFALLS.md — read before touching sync.py or providers
- COMMANDS.md, REPO.md, STYLE.md — as needed
What this project is
memsync solves a specific problem: Claude Code has no memory between sessions.
The standard fix is ~/.claude/CLAUDE.md, but it drifts, bloats, and doesn't
sync across machines.
memsync maintains one canonical GLOBAL_MEMORY.md in your cloud sync folder.
At session start, Claude Code reads it via a symlink (Mac/Linux) or copy (Windows)
at ~/.claude/CLAUDE.md. After meaningful sessions, the user runs
memsync refresh --notes "..." and the Claude API merges the notes in.
This is the identity layer — who the user is, what they're working on, standing preferences. Not project docs. Not cold storage. Not a knowledge base.
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.
- yesterday First seen · 93 lines · 894 tokens per session scan A b32360408611
memsync CLAUDE.md is an instructions file published in the GitHub repository EdgeCaser/memsync (2 stars, last pushed 1mo ago), licensed MIT. It adds 894 tokens to every session, about $0.0045 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain 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.