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.
curl -O https://raw.githubusercontent.com/marcelopaniza/mempenny/main/AGENTS.mdgit clone --depth 1 https://github.com/marcelopaniza/mempennyWrote 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/marcelopaniza/mempenny/agents-md)<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>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 | $0.01425 | $0.01425 |
| Opus 5 | $0.00713 | $0.00713 |
| Sonnet 5 | $0.00285 | $0.00285 |
| Haiku 4.5 | $0.00143 | $0.00143 |
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.
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.
- 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.
- ARCHIVE — completed-but-non-trivial. Move to
archive/, drop from theMEMORY.mdindex. Still searchable for forensics; out of the auto-load path. - DISTILL — 1-3 load-bearing facts buried in prose. Replace the narrative with the forward-looking conclusion. The most common action on aging files.
- 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.)
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 · 115 lines · 1,425 tokens per session scan A 386b00a854b7
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.
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.
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.
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).
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).
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.
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.