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/lopadova/claude-mem-sync/claude-mdgit clone --depth 1 https://github.com/lopadova/claude-mem-syncWhat 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 | $0.02871 | $0.02871 |
| Opus 5 | $0.01435 | $0.01435 |
| Sonnet 5 | $0.00574 | $0.00574 |
| Haiku 4.5 | $0.00287 | $0.00287 |
Grade A, and why
claude-mem-sync 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — claude-mem-sync
What this project is
claude-mem-sync is a TypeScript CLI tool and Claude Code plugin that enables curated, filtered, scored team memory sharing for claude-mem. It syncs AI memories across developers via git.
- Package name:
claude-mem-sync - CLI binary:
mem-sync - License: MIT
- Runtime: Bun (v1.0+) or Node.js (v18+)
- SQLite:
bun:sqliteon Bun,better-sqlite3on Node.js (auto-detected viasrc/core/compat.ts) - Runtime deps: Zod (config validation), better-sqlite3 (optional — only needed on Node.js)
Architecture
Developer Machine Shared Git Repo
┌─────────────────────┐ ┌──────────────────────┐
│ claude-mem SQLite DB │◄─ read-only─│ Export Pipeline │
│ (~/.claude-mem/) │ │ (filter + score) │──► contributions/
│ │ └──────────────────────┘
│ PostToolUse Hook ────► access.db │ Import Pipeline │◄── merged/latest.json
│ (tracks real usage) │ │ (dedup + integrity) │
└─────────────────────┘ └──────────────────────┘
GitHub Action merges contributions → merged/
│
┌──────────────────────┐ │
│ Profile Pipeline │◄────────────┤
│ (per-dev metrics) │──► profiles/│
└──────────────────────┘ │
┌──────────────────────┐ │
│ Distillation Pipeline│◄────────────┘
│ (LLM → rules + KB) │──► distilled/
└──────────────────────┘
Key invariants:
- Export pipeline and hook are read-only on claude-mem's DB
- Only the import pipeline writes to claude-mem's DB (with transaction rollback safety)
- access.db (
~/.claude-mem-sync/access.db) is our own tracking DB — never touches claude-mem's schema - All SQLite connections use
PRAGMA busy_timeout = 5000for WAL contention handling - Dedup uses composite key:
sdk_session_id + title + created_at_epoch(NOT the auto-incrementid)
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 · 216 lines · 2,871 tokens per session scan A b6d86a7abac5
claude-mem-sync CLAUDE.md is an instructions file published in the GitHub repository lopadova/claude-mem-sync (24 stars, last pushed 2mo ago), licensed MIT. It adds 2,871 tokens to every session, about $0.0144 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 2026-08-30.
Other instructions, from other repositories
claude-mem CLAUDE.md
Instructions for thedotmack/claude-mem, covering claude-mem: ai development instructions, build, file locations, requirements and documentation.
claude-mem copilot-instructions.md
Instructions for thedotmack/claude-mem, a project described as: Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot…
vexic AGENTS.md
Instructions for PyroDonkey/vexic, covering vexic agent instructions, project, architecture boundaries, package boundary and host ports.
vexic CLAUDE.md
Instructions for PyroDonkey/vexic: Root pointer for Claude Code working in this repository.
claude-dejavu AGENTS.md
Instructions for cmg8431/claude-dejavu, covering ai agent guidelines, commit message convention, types, architecture overview and core loop.
hindsight CLAUDE.md
Instructions for vectorize-io/hindsight, covering claude.md, project overview, development commands, local development (api + ui) and start both api server and control plane ui.