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/rexleimo/aios/memonpx skills add rexleimo/aios --skill memogit clone --depth 1 https://github.com/rexleimo/aiosWrote 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/rexleimo/aios/memo)<a href="https://agentmods.dev/skills/rexleimo/aios/memo"><img src="https://agentmods.dev/badge/skills/rexleimo/aios/memo.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 5.1 | $0.00094 | $0.00886 |
| Opus 5 | $0.00047 | $0.00443 |
| Sonnet 5 | $0.00019 | $0.00177 |
| Haiku 4.5 | $0.00009 | $0.00089 |
Grade A, and why
memo 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 2d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIOS Memory (memo)
Working directory: project root. Memory commands run from the repo root.
Principle: you decide, the harness executes
The harness only provides capabilities and does not judge semantics for you. Judging whether a fact is durable, what to persist, what to correct, and which recalled memory was useful is entirely your job. The harness parses your declaration and executes it — it never guesses for you.
Capabilities you can invoke
Run from the repo root with node scripts/aios.mjs memo ...:
- Recall what you already know before continuing work:
node scripts/aios.mjs memo recall [query]— human-readable session recall digest - Search prior memos (superseded facts hidden by default):
node scripts/aios.mjs memo search "<query>" [--limit N] - Persist a durable fact you just established:
node scripts/aios.mjs memo add "<fact>"— defaults to an appropriate scope; add--scope project_sharedfor facts anyone in the repo benefits from - Supersede a previously recorded fact you now know is wrong:
node scripts/aios.mjs memo add "<corrected fact>" --supersedes <eventId> - Mark useful a recalled memory that actually shaped your outcome:
node scripts/aios.mjs memo useful <eventId>
Run node scripts/aios.mjs memo --help for exact flags.
When to persist (you judge)
Persist a durable, verified fact that a future you or a teammate will need — e.g. a
root cause you established, a fix you ran and confirmed, a decision rule. Do not
persist chatter, greetings, or in-progress noise. There is no automatic write: if you
do not record it, it is not remembered. When in doubt, prefer project_shared for
facts anyone in the repo benefits from, agent_private for personal working notes.
Declaration block (drives the automatic loop)
The harness injects a ## AIOS MEMORY DECLARATION instruction into your prompt. At the
end of your reply, append one trailing block when this turn produced something durable:
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.
- 2d ago First seen · 76 lines · 94 tokens per session scan A dd7dd3c56596
memo is a skill published in the GitHub repository rexleimo/aios (52 stars, last pushed today), licensed MIT. It adds 94 tokens to every session and 886 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…
obsidian
Use the official Obsidian CLI (v1.12+) to manage vaults, notes, daily notes, search, tasks, tags, properties, links, templates, sync, publish, and workspaces. Use when the user mentions Obsidian, vaults, notes, or wants to automate note-taking and knowledge base workflows.
memory-state
State variables the Sentinel must keep across ticks (last order sent, freeze flag, FATAL streak, per-state counters, emergency history, cooldowns). Use this skill on every tick to update memory and decide if a new order is required (edge-triggered).
captain-diary
Daily handoff diary for the Captain. The Captain is restarted often (context-refresh, new work window, reboot) and otherwise loses the day's hard-won pacing lessons — repeating the same mistakes (e.g. 3 Scouts at once → an unbrakable spike → a 5h coast to repay the debt). Read the PREVIOUS day's notes at startup…
context-search
이전 세션 컨텍스트 검색 및 연속성 유지 스킬.
auto-why
의사결정 근거 조회 — Lore, SPEC, ARCHITECTURE에서 이유를 추적합니다.