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/asanabrial/leteo/agents-mdgit 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/instructions/asanabrial/leteo/agents-md)<a href="https://agentmods.dev/instructions/asanabrial/leteo/agents-md"><img src="https://agentmods.dev/badge/instructions/asanabrial/leteo/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 | $0.01553 | $0.01553 |
| Opus 5 | $0.00776 | $0.00776 |
| Sonnet 5 | $0.00311 | $0.00311 |
| Haiku 4.5 | $0.00155 | $0.00155 |
Grade A, and why
leteo 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 today.
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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on Leteo
Local-first persistent memory for coding agents: one Rust binary over one SQLite
database. Read openspec/project.md first — it says what
the crate is and how it is laid out.
Everything written into this repository is in English — code, comments,
commit messages, tests, and the documents under openspec/ — whatever language
the conversation about it happens in.
Keep openspec/ current
openspec/ is the written half of this project: one file per capability, saying
what the system guarantees and why. It is maintained as part of the work, not
after it.
- A change to a promise and its spec edit belong in the same commit. A commit that leaves a spec describing behaviour the code no longer has is worse than no documentation, because a reader will believe the wrong one.
- Keep it structured. Each spec has the same five sections — Purpose,
Behaviour, Invariants, Where it lives, Related — and the requirements under
Behaviour are numbered so they can be cited (
search.md §3). Numbers are stable; a requirement that stops holding is rewritten in place, never silently renumbered. - Keep it related. Every file ends with links to its neighbours, so any file is a way in to all of them. A fact that belongs in two specs lives in one and is linked from the other — stated twice, it will be edited once.
- Keep it readable. A spec longer than one sitting is two specs.
openspec/README.md lists exactly which kinds of change
require a spec edit. Read it before adding a tool, a command, a flag, a
doctor check, a migration, an output field, or a default.
Building and testing
cargo fmt --all
cargo clippy --all-targets
cargo test # unit tests, plus the integration tests in tests/
cargo build --release
All three must be clean before a commit. cargo test --lib alone is not enough:
it skips tests/, which is where the surface-level guards live.
Rules that have cost this codebase real bugs
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.
- today Changed · +6 lines · +100 tokens per session 4f98c52305fa
- 4d ago First seen · 118 lines · 1,453 tokens per session scan A ee26cba66df3
leteo AGENTS.md is an instructions file published in the GitHub repository asanabrial/leteo (2 stars, last pushed 2d ago), licensed MIT. It adds 1,553 tokens to every session, about $0.0078 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 instructions, from other repositories
memex AGENTS.md
Instructions for iamtouchskyer/memex, covering memex — agent working instructions, what is this, before you touch anything, how the code is layered and files you'll actually need.
gomaa CLAUDE.md
Claude Code instructions for M4F-S/gomaa, covering 🎯 agent operational directives & execution protocol, role & objective, core rules and execution protocol.
brain-os AGENTS.md
Instructions for brainOS-HQ/brain-os, covering agents.md, context, the hard rule, tool routing (in order) and mutation safety.
gnosys AGENTS.md
AGENTS.md instructions for proticom/gnosys, covering agents.md, what is gnosys, quick reference, architecture and key rules.
brain-os copilot-instructions.md
Instructions for brainOS-HQ/brain-os, covering github copilot instructions, read this first, critical rules (also in agents.md) and known bugs (v0.4.1 fixes pending).
superlocalmemory AGENTS.md
AGENTS.md instructions for qualixar/superlocalmemory, covering gitnexus — code intelligence, always do, never do, resources and cli.