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.
npx agentmods add instructions/lionellau/leptin/agents-mdgit clone --depth 1 https://github.com/lionellau/leptinWrote 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/lionellau/leptin/agents-md)<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>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 | $0.00713 | $0.00713 |
| Opus 5 | $0.00357 | $0.00357 |
| Sonnet 5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00071 | $0.00071 |
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) 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.
- Before acting on a project decision — package manager, framework, deploy
region, auth scheme, file conventions, anything your human has decided —
call
recallfirst. What comes back is the current resolved truth; reversed decisions are already removed. Trust it over your own assumptions. - 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). Usemtype="lesson"for a mistake you must never repeat.
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.
- 3d ago First seen · 61 lines · 713 tokens per session scan B 59eaea48a54a
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.
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.
varve CLAUDE.md
Instructions for varve-sh/varve, covering varve, memory tools, rules (always follow) and what actually happens when you call these tools.
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).
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.
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 ──.
honcho CLAUDE.md
Claude Code instructions for plastic-labs/honcho, covering claude.md, honcho overview, what is honcho?, core concepts and peer paradigm.