letta-ai/letta-code is an agent harness for building assistants that retain memory, identity, and experience across interactions instead of treating each task as isolated. Developers use it through local, desktop, browser, or messaging interfaces for interactive or continuously running agents, and its catalogue entries configure the agents' skills, instructions, rules, and behavior.
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 skills add letta-ai/letta-code --skill customizing-commandsgit clone --depth 1 https://github.com/letta-ai/letta-codeWrote 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/skills/letta-ai/letta-code/customizing-commands)<a href="https://agentmods.dev/skills/letta-ai/letta-code/customizing-commands"><img src="https://agentmods.dev/badge/skills/letta-ai/letta-code/customizing-commands/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/letta-ai/letta-code/customizing-commands"><img src="https://agentmods.dev/badge/skills/letta-ai/letta-code/customizing-commands.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.00849 |
| Opus 5.5 | $0.00020 | $0.00340 |
| Sonnet 5.5 | $0.00010 | $0.00170 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
customizing-commands 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 1mo 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customizing Commands
Use this as the command-specific entrypoint for local mod slash commands. For broader mod work, recipes live in ../creating-mods/references/commands.md, ../creating-mods/references/architecture.md, ../creating-mods/references/ui.md, and ../creating-mods/references/plan-mode.md.
Mod files live in:
~/.letta/mods/
Use a focused file name, e.g. ~/.letta/mods/review.ts or ~/.letta/mods/commands.ts.
First decide whether a command is right
| User wants | Build |
|---|---|
/foo sends a prompt or shows local output |
Mod command |
/foo starts a reusable agent workflow |
Skill + thin mod command |
| Agent/model should autonomously call the capability | Mod tool, not a command |
| Command shows transient progress/results | Mod command + panel |
| Command needs model output while the main agent is busy | runWhenBusy: true command + forked ctx.conversation |
If the command is a reusable workflow like /goal, put the workflow instructions in a skill and keep the mod command as a small launcher/prompt.
Workflow
- Inspect
~/.letta/mods/for related command files. - Preserve unrelated mod code; create a focused new file if merging is messy.
- Register with
letta.commands.register()and guard withletta.capabilities.commands. - Return the unregister function, or a disposer that calls it plus any timer/panel cleanup.
- Tell the user the exact file path changed and to run
/reload.
Default prompt command
export default function activate(letta) {
if (!letta.capabilities.commands) return;
return letta.commands.register({
id: "review",
description: "Review current git changes",
args: "[focus]",
run(ctx) {
const focus = ctx.args.trim();
return {
type: "prompt",
content: focus
? `Review current git changes. Focus on ${focus}.`
: "Review current git changes. Focus on correctness issues.",
systemReminder: true,
};
},
});
}
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.
- 1mo ago First seen · 91 lines · 49 tokens per session scan A e09575b71ed1
customizing-commands is a skill published in the GitHub repository letta-ai/letta-code (3,625 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 849 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
memory-import
Bulk-import an external knowledge base into Prismer memory via the three-layer import pipeline (07 §3.1). Use when the user asks to import/migrate documents, a knowledge base, or notes into workspace memory. Layer 1 lands raw documents (zero LLM, instantly searchable); Layer 2 is YOUR distillation work — you read the…
food-order
Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.