What is elfmem AGENTS.md?

A set of repository instructions for elfmem, a memory system for AI coding agents. It explains the difference between identity memory, which follows the agent, and session memory, which belongs to the project and harness.

Use it when deciding where an agent should save or retrieve information in the elfmem repository. It covers vendor-neutral agent guidance and the routing rule between the two memory systems.

It prevents agents from saving information in the wrong memory system, which could make shared learning unavailable or cause project-specific details to persist incorrectly.

How emson/elfmem configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to emson/elfmem. 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/emson/elfmem/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/emson/elfmem

Made for: Codex, OpenCode.

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/emson/elfmem/agents-md/github.svg)](https://agentmods.dev/instructions/emson/elfmem/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/emson/elfmem/agents-md"><img src="https://agentmods.dev/badge/instructions/emson/elfmem/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/emson/elfmem/agents-md"><img src="https://agentmods.dev/badge/instructions/emson/elfmem/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 929 This file is loaded in full into every session.

When invoked 929 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	$0.00929	$0.00929
Opus 5.5	$0.00372	$0.00372
Sonnet 5.5	$0.00186	$0.00186
Haiku 4.5	$0.00093	$0.00093

Measured 2mo ago against content hash edac4137ef0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

elfmem 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 2mo 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.

AGENTS.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guide — elfmem

Vendor-neutral guidance for any AI coding agent (Claude Code, Cursor, Codex, Aider, Cody, Continue, …) working in this repository.

Tool-specific addenda live in CLAUDE.md — paths, harness behaviours, and anything that only applies to one agent. Anything that would help any agent get the elfmem semantics right belongs here.

If you maintain another agent tool and discover guidance you wish you'd had: add it to this file, not a sibling.

Memory routing — identity memory vs. session memory

Two memory systems are available to agents working in this repo. They look symmetric (both save "facts for later") but address different identities, and confusing them silently bypasses elfmem's learning mechanism.

The two systems

Identity memory — elfmem

Owner: elf (or, for derived projects, whichever agent the elfmem instance represents).
Persistence: peer-shareable, survives project deletion, consolidated by dream(), decay-aware.
Access: elfmem CLI, the elfmem MCP tool family, or MemorySystem.learn() / .remember() from Python.

Session memory — agent harness memory

Owner: the agent's harness, scoped to this project directory.
Persistence: auto-loaded by the harness at session start; lost if the project is deleted; not peer-shared.
Access: tool-specific. Examples:
- Claude Code: ~/.claude/projects/<encoded-path>/memory/MEMORY.md
- Cursor: .cursorrules and cursor-rules directories
- Codex: project-scoped notes
- Aider: .aider.conf.yml and chat history
- Continue: .continuerc.json and config-local rules

The routing rule

Cheapest disambiguation first; stop at the first one that fires.

Verb-level shibboleth
- "learn as elf" / "remember about elf" / "store as Mira" → identity memory.
- "note for this session" / "remember for this repo" → session memory.
- The identity claim in the verb is the routing signal.
Survival test
- Would this fact still matter if this project directory were deleted tomorrow? Yes → identity memory. No → session memory.

Read the full file on GitHub · 101 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.

2mo ago First seen · 101 lines · 929 tokens per session scan A edac4137ef0b

Subscribe to this mod's changes

elfmem AGENTS.md is an instructions file published in the GitHub repository emson/elfmem (59 stars, last pushed 1mo ago), licensed MIT. It adds 929 tokens to every session, about $0.0037 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 2026-08-30.

Memory and context

elfmem AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
elfmem AGENTS.mdemson/elfmem	Instructions file	59	1mo ago	MIT	A	929	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

elfmem: Instructions file for Codex