Borrowing it
Nothing to install: this file belongs to justfortytwo/memory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/justfortytwo/memory/main/AGENTS.mdgit clone --depth 1 https://github.com/justfortytwo/memoryWrote 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.
[](https://agentmods.dev/instructions/justfortytwo/memory/agents-md)<a href="https://agentmods.dev/instructions/justfortytwo/memory/agents-md"><img src="https://agentmods.dev/badge/instructions/justfortytwo/memory/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/justfortytwo/memory/agents-md"><img src="https://agentmods.dev/badge/instructions/justfortytwo/memory/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02623 | $0.02623 |
| Opus 5.5 | $0.01049 | $0.01049 |
| Sonnet 5.5 | $0.00525 | $0.00525 |
| Haiku 4.5 | $0.00262 | $0.00262 |
Grade A, and why
memory AGENTS.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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working in @justfortytwo/memory.
What this is
A standalone, persona-agnostic semantic-memory MCP server (npm: @justfortytwo/memory,
bin fortytwo-memory). It stores text memories with free-form provenance and recalls them
semantically (sqlite-vec), lexically (FTS5), or by structured filter. Storage is SQLite via
better-sqlite3 + knex. Embeddings come from Ollama by default, an opt-in OpenAI-compatible
provider, or a deterministic FakeEmbedder when EMBED_MODEL is unset. It is also a Claude Code
plugin (.claude-plugin/plugin.json + .mcp.json) and a library imported by sibling packages.
Layout
src/
index.ts bin entry + public library re-exports (server boot guarded by invokedAsBin())
server.ts MCP Server: ListTools/CallTool + INSTRUCTIONS text sent on initialize
tools.ts MCP wire schema for the tool surface (toolDefinitions)
dispatch.ts callTool(): routes tool name+args to memory.ts (transport-free, unit-testable)
contract.ts MEMORY_TOOL_CONTRACT_VERSION, memoryToolContract, MEMORY_SERVER_ID
memory.ts core ops: store/query/recall/recallDocs/lexical/reindex/exportRange/reembed/deleteByIds
embedder.ts Embedder interface, FakeEmbedder, OllamaEmbedder, OpenAICompatEmbedder, embedderFromEnv
db.ts openDb(): raw better-sqlite3 handle (+ sqlite-vec, vec0 tables) and a knex handle; EMBED_DIM=1024
migrate.ts runMigrations() with a static migration list; also the `npm run migrate` entry
migrations/00N_*.ts 001_init, 002_fts, 003_approvals, 004_jobs
enrichment.ts enrich / enrichFromTurn (dedupe + write; salience extractor is injected)
jobs.ts durable jobs queue (enqueue/claimDue/complete/fail/requeueStale/...) used by scheduler
gate-approval-store.ts GateApprovalStore: SQLite impl of @justfortytwo/gate's ApprovalStore + AuditLogger
test/*.test.ts vitest suites (one per module, plus gate-seam cross-package test)
.github/workflows/ci.yml calls the shared justfortytwo/.github node-ci.yml workflow with siblings: "gate"
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.
- 13d ago First seen · 214 lines · 2,623 tokens per session scan A 580aac16a38b
memory AGENTS.md is an instructions file published in the GitHub repository justfortytwo/memory (0 stars, last pushed 9d ago), licensed MIT. It adds 2,623 tokens to every session, about $0.0105 per session on Opus 5.5. 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 2026-10-09.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.