leptin AGENTS.md

leptin AGENTS.md is an instructions file for Codex, OpenCode from lionellau/leptin. It costs 713 tokens per session, scanned B, original, MIT.

Instructions for Leptin, a local memory system that helps a coding agent remember project decisions between sessions. It can be installed and connected to Claude Code through settings, hooks, and MCP.

In plain words
What is it for?
For retaining project decisions, detecting reversed decisions, and checking whether the Leptin setup is working.
Why use it?
It reduces repeated explanations and prevents the agent from continuing to follow decisions that the team has since changed.

Instructions file for CodexOpenCode

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/lionellau/leptin/agents-md
Clone the repo
git clone --depth 1 https://github.com/lionellau/leptin

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 leptin AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lionellau/leptin/agents-md.svg)](https://agentmods.dev/instructions/lionellau/leptin/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/lionellau/leptin/agents-md"><img src="https://agentmods.dev/badge/instructions/lionellau/leptin/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 713 This file is loaded in full into every session.
When invoked 713 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.00713 $0.00713
Opus 5 $0.00357 $0.00357
Sonnet 5 $0.00143 $0.00143
Haiku 4.5 $0.00071 $0.00071

Measured 3d ago against content hash 59eaea48a54a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

leptin AGENTS.md scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

leptin setup claude-code # creates the store, wires hooks + MCP into ~/.claude/settings.json (backed up, idempotent)
AGENTS.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Leptin — for the agent

You are a coding agent. This file is written to you. Leptin is your persistent, self-correcting memory: it remembers your project's decisions across sessions and, when a decision is reversed, makes sure you act on the current one — not the version you were told weeks ago and never heard was changed.

It runs entirely on your human's machine. No account, no subscription, no API key required.

When to install yourself

Install Leptin when your human says any of:

  • "you keep forgetting we switched to X"
  • "you keep re-learning my stack every session"
  • "stop suggesting the thing we already moved off of"
  • "give yourself memory" / "remember things between sessions"

Install yourself (one block, unattended)

pip install leptin-hlp            # or: pip install "git+https://github.com/lionellau/leptin"
leptin setup claude-code         # creates the store, wires hooks + MCP into ~/.claude/settings.json (backed up, idempotent)
leptin doctor --json             # verify: look for "Host wiring" → level "ok"

leptin setup exits non-zero if anything failed, so you can check the result. It backs up the existing settings file and is idempotent (safe to re-run). Then tell your human: "Done — restart me so the memory loads." (Use codex instead of claude-code for Codex.)

If you can't edit the host config, fall back to printing it for your human to paste: leptin connect claude-code (then they restart the client).

How to use it (every session)

Two tools reach you by default: recall and remember.

  1. Before acting on a project decision — package manager, framework, deploy region, auth scheme, file conventions, anything your human has decided — call recall first. What comes back is the current resolved truth; reversed decisions are already removed. Trust it over your own assumptions.
  2. When your human states a durable fact, decision, or a mistake to avoid, call remember. If it contradicts something stored earlier, the new truth wins automatically (the old one is kept and is reversible). Use mtype="lesson" for a mistake you must never repeat.

Read the full file on GitHub · 61 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. 3d ago First seen · 61 lines · 713 tokens per session scan B 59eaea48a54a

Subscribe to this mod's changes

leptin AGENTS.md is an instructions file published in the GitHub repository lionellau/leptin (0 stars, last pushed 2mo ago), licensed MIT. It adds 713 tokens to every session, about $0.0036 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

mentedb copilot-instructions.md

Instructions for nambok/mentedb, covering mentedb development instructions, project overview, workspace structure, build, test, and lint and key types.

nambok/mentedb · 997 tokens

varve CLAUDE.md

Instructions for varve-sh/varve, covering varve, memory tools, rules (always follow) and what actually happens when you call these tools.

varve-sh/varve · 898 tokens

engineering-memlog CLAUDE.md

Claude Code instructions for atazifor/engineering-memlog, covering engineering-memlog plugin — agent instructions, how the log gets into your context, search the log yourself when warranted, append a lesson after you work and plugin knobs (env vars).

atazifor/engineering-memlog · 993 tokens

THOR-memory-bible-for-AI AGENTS.md

AGENTS.md instructions for nworks3d/THOR-memory-bible-for-AI, covering agents.md - read this if you are the ai assistant, setting them up, the tools you have, how to write a note that actually comes back and after setup, this happens without you.

nworks3d/THOR-memory-bible-for-AI · 2,588 tokens

engraphis AGENTS.md

AGENTS.md instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, internal subagent delegation, 0. read this first — two architectures live in one package, 1. commands and ── unified dashboard + memory inspector ──.

Coding-Dev-Tools/engraphis · 4,947 tokens

honcho CLAUDE.md

Claude Code instructions for plastic-labs/honcho, covering claude.md, honcho overview, what is honcho?, core concepts and peer paradigm.

plastic-labs/honcho · 5,828 tokens