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 skills/asanabrial/leteo/memorynpx skills add asanabrial/leteo --skill memorygit clone --depth 1 https://github.com/asanabrial/leteoWrote 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/asanabrial/leteo/memory)<a href="https://agentmods.dev/skills/asanabrial/leteo/memory"><img src="https://agentmods.dev/badge/skills/asanabrial/leteo/memory.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 | $0.00038 | $0.03208 |
| Opus 5 | $0.00019 | $0.01604 |
| Sonnet 5 | $0.00008 | $0.00642 |
| Haiku 4.5 | $0.00004 | $0.00321 |
Grade A, and why
leteo-memory 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Leteo Persistent Memory — Protocol
You have access to Leteo, a persistent memory system that survives across sessions and compactions. This protocol is MANDATORY and ALWAYS ACTIVE — not something you activate on demand.
AVAILABLE TOOLS
The plugin registers Leteo with the agent tool profile, so the everyday tools
are present from the first message — no ToolSearch needed.
mem_save,mem_search,mem_context,mem_session_summarymem_get_observation,mem_timeline,mem_suggest_topic_key,mem_updatemem_session_start,mem_session_end,mem_save_promptmem_current_project,mem_pin,mem_unpin,mem_reviewmem_judge,mem_compare,mem_capture_passive,mem_doctor
Only the three that change or count the whole store are deferred; reach for
ToolSearch when you need one: mem_stats, mem_delete, mem_merge_projects.
If the tools are missing, run leteo setup claude-code and restart the
client. Verify the store itself with leteo doctor.
PROACTIVE SAVE TRIGGERS (mandatory — do NOT wait to be asked)
Call mem_save IMMEDIATELY after any of these:
After decisions or conventions
- An architecture or design decision was made
- A team convention was established
- A tool or library was chosen, with its tradeoffs
After completing work
- A bug was fixed — record the root cause, not just the symptom
- A feature landed with a non-obvious approach
- A configuration or environment change was made
After discoveries
- Something non-obvious about the codebase
- A gotcha, edge case, or surprising behaviour
- A pattern worth repeating
After the user confirms or rejects something
- The user accepts a recommendation ("go with that", "perfect", or the equivalent in their language)
- The user rejects an option ("no, better X")
- The user states a preference or constraint
Self-check after EVERY task
"Did we just decide something, fix a bug, learn something non-obvious, or establish a convention? If yes, call
mem_savenow."
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 · 293 lines · 38 tokens per session scan A d44959402649
leteo-memory is a skill published in the GitHub repository asanabrial/leteo (2 stars, last pushed 6d ago), licensed MIT. It adds 38 tokens to every session and 3,208 once invoked, about $0.0002 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 skills, from other repositories
memory-curation
When you have read / processed a workspace asset in this session and learned something durable about it, write a memory page so future sessions benefit. Maintain the workspace wiki's hierarchical structure as it grows.
memory
Persist and retrieve agent memory across sessions — write durable notes, read by path, recall via semantic search, list/delete, and consolidate. Use whenever the user asks to remember/forget something, when you need to look up past decisions or context, or when episodic state matters beyond the current turn. Executes…
recall
Recall this repository's OwnMem local memory before changing code, and keep it healthy. Use when a repository contains .ownmem/, when past debugging lessons could apply ("have we hit this before", "why is it done this way"), or when the user mentions ownmem, project memory, or recalling across sessions.
dashboard
Open OwnMem Console, the local dashboard for this repository's memory. Use when the user asks to open the dashboard, see memory metrics, check adoption or recall quality, or set up the optional embedding lane. Requires a repository initialized with the dashboard layer.
init
Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.
docmancer
Work from the same local memory as every other coding agent on this machine. Recall prior decisions, preferences, instructions, and project conventions that Claude Code, Codex, Cursor, and other agents wrote here, with cited sources, fully local. Also searches a separate local technical-documentation index.