mempenny: Instructions file for Codex

AGENTS.md

mempenny AGENTS.md is an instructions file for Codex, OpenCode from marcelopaniza/mempenny. It costs 1,425 tokens per session, scanned A, original, MIT.

A set of instructions for MemPenny, a tool that cleans up the saved memory an AI coding agent uses between sessions. It explains what MemPenny does, where memory is stored, and how its cleanup rules work.

In plain words
What is it for?
It helps an agent find its memory directory, apply MemPenny’s cleanup strategy, and maintain topic-based memory files across different coding-agent tools.
Why use it?
AI agents can accumulate outdated notes, replaced decisions, and lengthy reports that make future sessions harder to use. These instructions keep memory smaller and organized while preserving reversible backups.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions AGENTS.md.

This is marcelopaniza/mempenny's own configuration. It tells Codex and OpenCode how to work on mempenny itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mempenny configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/you/app.

Reuse

Borrowing it

Nothing to install: this file belongs to marcelopaniza/mempenny. 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/marcelopaniza/mempenny/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/marcelopaniza/mempenny

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.

agentmods badge for mempenny AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/marcelopaniza/mempenny/agents-md.svg)](https://agentmods.dev/instructions/marcelopaniza/mempenny/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/marcelopaniza/mempenny/agents-md"><img src="https://agentmods.dev/badge/instructions/marcelopaniza/mempenny/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,425 This file is loaded in full into every session.
When invoked 1,425 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 5.1 $0.01425 $0.01425
Opus 5 $0.00713 $0.00713
Sonnet 5 $0.00285 $0.00285
Haiku 4.5 $0.00143 $0.00143

Measured 6d ago against content hash 386b00a854b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mempenny 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 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.

AGENTS.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

MemPenny — memory hygiene for any AI coding agent. This file is the host-agnostic ruleset. Claude Code and opencode load it automatically alongside the full /mempenny-* commands; every other agent (Codex, Gemini, CodeWhale, Swival, Cursor, Windsurf, …) reads this file for the strategy, guards, and procedure.

What MemPenny does

An agent's memory directory grows over time — old incident notes, superseded decisions, verbose postmortems. The cost is paid on every new session that loads it. MemPenny tidies the directory: drops the stale, archives the historical, distills the verbose to a line or two, and keeps what's left in a small fixed set of topic files. Backup-first, always reversible.

Where the memory lives

The default memory directory is Claude Code's auto-memory layout: ~/.claude/projects/<project-slug>/memory/, where <project-slug> is the project's absolute path with every / replaced by - (a project at /home/you/app keeps its memory in ~/.claude/projects/-home-you-app/memory/). Claude Code and opencode resolve this automatically. On any other host, tell the agent where the memory directory is — this path, or wherever yours lives — before asking it to read or tidy anything.

The strategy hierarchy

Cheapest action first. Always pick the cheapest one that applies.

  1. DELETE — the content is truly obsolete. The fix is in the code; a one-shot bug with no future implication; marked "RESOLVED" / "do not re-fix"; superseded by a newer file on the same topic.
  2. ARCHIVE — completed-but-non-trivial. Move to archive/, drop from the MEMORY.md index. Still searchable for forensics; out of the auto-load path.
  3. DISTILL — 1-3 load-bearing facts buried in prose. Replace the narrative with the forward-looking conclusion. The most common action on aging files.
  4. KEEP — active state, architecture, recurring rule, or already-tight prose.

(COMPRESS — shrinking prose that's already been triaged — is out of scope here. Triage first; compress survivors separately if you want extra savings.)

Read the full file on GitHub · 115 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.

  1. 6d ago First seen · 115 lines · 1,425 tokens per session scan A 386b00a854b7

Subscribe to this mod's changes

mempenny AGENTS.md is an instructions file published in the GitHub repository marcelopaniza/mempenny (2 stars, last pushed 17d ago), licensed MIT. It adds 1,425 tokens to every session, about $0.0071 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.

Related

Other instructions, from other repositories

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

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens