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/masikgit/memser/claude-mdgit clone --depth 1 https://github.com/masikgit/memserWhat 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 | $0.01480 | $0.01480 |
| Opus 5 | $0.00740 | $0.00740 |
| Sonnet 5 | $0.00296 | $0.00296 |
| Haiku 4.5 | $0.00148 | $0.00148 |
Grade A, and why
memser 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
An MCP server ("memser") that exposes tiered, persistent memory operations
(store_memory, recall_memory, forget_memory, consolidate_memories,
list_memories) as MCP tools, so any MCP-compatible agent can plug in for
long-term memory. See README.md for the full tool reference and
data model.
Commands
# Setup
cp .env.example .env
docker compose up -d # Postgres+pgvector and Redis
pip install -e ".[dev]"
python -m scripts.init_db # only if not relying on docker-compose's auto-init
# Run
python -m app.server # MCP server over stdio
mcp dev app/server.py # run with the MCP inspector for local iteration
# Test
pytest # full suite
pytest tests/test_scoring.py -q # single file
pytest tests/test_consolidation.py::test_cluster_by_similarity_groups_close_vectors # single test
Tests are pure-logic unit tests (scoring math, hash-embedder determinism, clustering, summarization fallback) — none require Postgres/Redis to be running. There is no integration suite against a live database yet.
There is no lint/format tooling configured in this repo yet — don't assume ruff/black/mypy are wired up unless you add them.
Architecture
Four layers, each in its own module, called top-down:
app/server.py MCP tools (thin) — opens a session, calls the engine, returns .model_dump(mode="json")
app/memory_engine.py store/recall/forget/list logic: dedup, conflict resolution, hybrid ranking
app/consolidation.py episodic -> semantic clustering + summarization
app/jobs.py APScheduler jobs that call consolidation/decay on a timer
app/scoring.py pure scoring math, no I/O
app/embeddings.py embedding provider abstraction (OpenAI or local fallback)
app/redis_client.py working-tier (Redis) reads/writes
app/models.py, db.py Postgres schema (SQLAlchemy) + async engine/session
app/audit.py writes to memory_audit_log
app/config.py pydantic-settings, reads .env
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 · 124 lines · 1,480 tokens per session scan A 2f1f55707eaf
memser CLAUDE.md is an instructions file published in the GitHub repository masikgit/memser (0 stars, last pushed 21d ago), licensed Apache-2.0. It adds 1,480 tokens to every session, about $0.0074 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
vscode buildNext.instructions.md
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).
spec-kit AGENTS.md
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.
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.
langchain AGENTS.md
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.
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).
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.