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/letta-ai/letta-code/agents-mdgit clone --depth 1 https://github.com/letta-ai/letta-codeWhat 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 | $0.10832 | $0.10832 |
| Opus 5 | $0.05416 | $0.05416 |
| Sonnet 5 | $0.02166 | $0.02166 |
| Haiku 4.5 | $0.01083 | $0.01083 |
Grade A, and why
letta-code 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 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.
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 — 948 lines — stays where its author put it; the contents beside it link to each section on GitHub.
letta-code — Agent Guide
This file explains how to work effectively in this repo. It covers the rules enforced by CI, why each rule exists, and the workflow conventions that keep the codebase healthy and agent-navigable.
Workflow
- Create a worktree for any non-trivial change — especially if another agent may be working concurrently.
- Make your change, then run
bun run checkand fix all failures before opening a PR. - One PR per logical change. Don't bundle unrelated changes — harder to revert if something breaks.
- Never amend commits. Always create a new commit.
- Check the current branch before editing files. If in doubt, ask.
Runtime Validation
Development and distribution use different runtimes. bun run dev runs the
TypeScript source with Bun, while the published package exposes a Node-targeted
letta.js bundle and requires Node 22.19 or newer. When behavior depends on the
runtime, test both the Bun source path and the built Node artifact.
The interactive TUI, headless mode, and websocket listener also have separate
orchestration paths. Changes to shared turn, tool, approval, permission, or
transcript behavior must identify and run the focused tests for every affected
path. bun run check is always required, but it does not replace those behavior
tests.
Rules and Why They Exist
These are the rules enforced by CI and the pre-commit hook, with the reasoning behind each. Understanding the why lets you make good decisions in ambiguous cases the rules don't explicitly cover.
No ../ parent imports — use @/
Rule: All cross-directory imports must use the @/ alias (@/ maps to src/). Relative parent paths (../) are banned and blocked by pre-commit.
Why: Agents navigate codebases by searching. import { getBackend } from "@/backend" is immediately grep-discoverable anywhere in the repo. import { getBackend } from "../../backend" requires resolving the path from the current file's location — fragile to moves and opaque to search. Consistent absolute paths also make codemods reliable: a rename script can find all import sites with a simple grep.
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 · 948 lines · 10,832 tokens per session scan A f1db6b58e260
letta-code AGENTS.md is an instructions file published in the GitHub repository letta-ai/letta-code (3,178 stars, last pushed yesterday), licensed Apache-2.0. It adds 10,832 tokens to every session, about $0.0542 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 2026-08-30.
Other instructions, from other repositories
m_flow AGENTS.md
AGENTS.md instructions for FlowElement-xinliuyuansu/m_flow, covering m-flow — developer & agent reference, 1. repository map, extension points, 2. local development and python backend (requires python 3.10 – 3.13).
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
docmancer copilot-instructions.md
Instructions for docmancer/docmancer, covering docmancer, workflow and core commands.
memex GEMINI.md
Instructions for STiFLeR7/memex, covering memex, agent instructions, execution mode, non-negotiables and what is in scope.
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.
Agent-Memory-Bridge AGENTS.md
Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.