What is memtomem-stm CLAUDE.md?

Repository instructions for memtomem-stm, a short-term memory proxy that connects software to an MCP service for temporary memory. They document required checks and rules for editing the project.

Use them when changing memtomem-stm, validating its documentation, running its Python checks, or testing its tutorial and mocked Ollama integrations.

They help an agent follow the project’s Python version, cross-platform requirements, documentation checks, linting, type checking, and test commands.

How memtomem/memtomem-stm configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to memtomem/memtomem-stm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/memtomem/memtomem-stm/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/memtomem/memtomem-stm

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/memtomem/memtomem-stm/claude-md.svg)](https://agentmods.dev/instructions/memtomem/memtomem-stm/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/memtomem/memtomem-stm/claude-md"><img src="https://agentmods.dev/badge/instructions/memtomem/memtomem-stm/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 601 This file is loaded in full into every session.

When invoked 601 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00601	$0.00601
Opus 5	$0.00300	$0.00300
Sonnet 5	$0.00120	$0.00120
Haiku 4.5	$0.00060	$0.00060

Measured 6d ago against content hash 82c0a500e6bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

memtomem-stm 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 6d 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 · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code notes — memtomem-stm

Short-term memory MCP proxy. What it does → README.md; setup and layout → CONTRIBUTING.md; architecture → docs/. This file holds only what must be known before reading those — everything else is a pointer, not a copy.

Commands

Requires Python 3.12+ and uv.

uv sync                                                    # install deps
uv run pytest -m "not bench_qa_meta and not bench_qa_llm_judge and not bench_qa_sweep and not bench_qa_drift and not bench_qa_perf"  # tests (CI filter)
uv run ruff check src && uv run ruff format --check src    # lint (required)
uv run mypy src                                            # typecheck (required)
uv run pytest tests/test_docs_sync.py tests/test_docs_links.py  # docs contracts
uv run pytest --nbmake notebooks/01_quickstart_proxy_setup.ipynb --nbmake-timeout=180  # public tutorial

ruff, mypy, and tests gate merge — on Windows too, so POSIX-only stdlib (fcntl, os.killpg, …) needs a sys.platform guard mypy can narrow. Live-Ollama tests are out of scope: Ollama paths are tested with mocked transport / dead ports only (#637).

Invariants when editing

No Python-level dependency on memtomem core. Don't import memtomem from src/ — STM reaches LTM only over MCP.
mms ≡ memtomem-stm-proxy ≡ memtomem-stm. Three entry points, one Click group; registering any of them as an MCP client's command must work identically. Dispatch rules: the cli group docstring in src/memtomem_stm/cli/proxy.py (#260).
Pipeline order is CLEAN → COMPRESS → SURFACE, plus an optional INDEX stage for custom embedders. Per-stage contracts: comments in src/memtomem_stm/proxy/ — authoritative, don't restate them here.
Line length 100, target py312.
.claude/ and scripts/ are gitignored except the tracked scripts/audit-dependencies.sh (release/CI gate) and scripts/core_compat_smoke.py (advisory compat check). Don't commit other files under them, and don't assume contributors share your local contents.
One focused change per PR, branched from main, with tests for new behavior and a commit message explaining the "why". Full checklist: CONTRIBUTING.md.

Read the full file on GitHub · 44 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.

6d ago First seen · 44 lines · 601 tokens per session scan A 82c0a500e6bb

Subscribe to this mod's changes

memtomem-stm CLAUDE.md is an instructions file published in the GitHub repository memtomem/memtomem-stm (5 stars, last pushed today), licensed Apache-2.0. It adds 601 tokens to every session, about $0.0030 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.

LLM ai-agents caching claude compression mcp

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

memtomem-stm: Instructions file for Claude Code