mnemex CLAUDE.md

mnemex CLAUDE.md is an instructions file for coding agents from notsointresting/mnemex. It costs 441 tokens per session, scanned A, original, MIT.

Project instructions for mnemex, a local tool that links coding decisions to specific files and symbols and checks whether those decisions are still current. It also defines rules for coordinating agents and checking their work.

In plain words
What is it for?
Use it when building or changing mnemex, especially for its decision records, context limits, local-first operation, installation support, and verification process.
Why use it?
It gives coding agents boundaries for safe, verifiable changes and limits how much context is injected. It helps prevent outdated decisions, unchecked merges, and accidental use of external services.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/notsointresting/mnemex/claude-md
Clone the repo
git clone --depth 1 https://github.com/notsointresting/mnemex

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.

agentmods badge for mnemex CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/notsointresting/mnemex/claude-md.svg)](https://agentmods.dev/instructions/notsointresting/mnemex/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/notsointresting/mnemex/claude-md"><img src="https://agentmods.dev/badge/instructions/notsointresting/mnemex/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 441 This file is loaded in full into every session.
When invoked 441 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00441 $0.00441
Opus 5 $0.00220 $0.00220
Sonnet 5 $0.00088 $0.00088
Haiku 4.5 $0.00044 $0.00044

Measured 3d ago against content hash 83454557e3d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mnemex 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 3d 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 · 33 lines

What it actually says

mnemex — Build Context

Goal

MCP server giving coding agents ANCHORED memory: every decision is bound to a file+symbol and hash-stamped, delivered JUST-IN-TIME via hooks. One SQLite file (sqlite-vec + FTS5). Distributed via MCP + skills + AGENTS.md across all agents.

Orchestration rules

  • Opus 4.8 orchestrates; delegate bounded deliverables to subagents with written contracts.
  • Subagents return diff + test results + self-report. Never blind-merge.
  • A phase is done ONLY when its verification gate passes (tests green + verifier's adversarial cases pass + objective metric met).
  • verifier-agent must be a SEPARATE spawn from the implementer. Authors don't grade themselves.
  • Build the ANCHOR core (Phase 1) before any indexer, using synthetic nodes.

Hard constraints

  • No cloud/external API for core features. Local-first.
  • Context injections respect hard token caps (800 session / 400 JIT). Never exceed.
  • pip install works on macOS/Linux/Windows, Py 3.10–3.13, no ML model required (no-ML mode).
  • Secrets/PII stripped at write time; Phase 6 security gate is blocking.
  • Prefer wrapping an existing structural backend over reinventing a parser (Path A).

Layout

mnemex/storage.py → sqlite-vec + FTS5, schema, migrations mnemex/anchors.py → anchor resolve + hash stamp + staleness (THE MOAT) mnemex/retrieval.py → BM25+vector RRF + token governor mnemex/indexer.py → structural backend adapter mnemex/server.py → FastMCP tools mnemex/hooks.py → SessionStart/PreToolUse/Stop, JIT injection mnemex/agents_md.py → self-updating AGENTS.md mnemex/security.py → secret stripping + audit log tests/fixtures/ → golden repo, Q→memory set, secret corpus, git history

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.

  1. 3d ago First seen · 33 lines · 441 tokens per session scan A 83454557e3d7

Subscribe to this mod's changes

mnemex CLAUDE.md is an instructions file published in the GitHub repository notsointresting/mnemex (1 stars, last pushed 1mo ago), licensed MIT. It adds 441 tokens to every session, about $0.0022 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.