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 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/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/rexleimo/aios/memo"><img src="https://agentmods.dev/badge/skills/rexleimo/aios/memo.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 | $0.00094 | $0.01596 |
| Opus 5.5 | $0.00038 | $0.00638 |
| Sonnet 5.5 | $0.00019 | $0.00319 |
| Haiku 4.5 | $0.00009 | $0.00160 |
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 8d 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 — 139 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 aios memo ... (the installed AIOS CLI — not a repo-relative script):
- Recall what you already know before continuing work:
aios memo recall [query]— human-readable session recall digest - Search prior memos (superseded facts hidden by default):
aios memo search "<query>" [--limit N] - Persist a durable fact you just established:
aios 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:
aios memo add "<corrected fact>" --supersedes <eventId> - Mark useful a recalled memory that actually shaped your outcome:
aios memo useful <eventId> - Checkpoint a milestone so future sessions recall it first (pinned memory):
aios memo checkpoint "<one-line takeaway>"— use at milestones and before claiming work complete
Run aios 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.
Extraction contract (shape of a persistable entry)
Before you persist — via the declaration conclusion= or memo add — shape the
fact as one self-contained entry carrying five elements:
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.
- 8d ago Changed a549c2b218f7
- 1mo ago Changed 3fd0f78c3a52
- 1mo ago Changed · +3 lines e17b99287edb
- 1mo ago Changed b468a8698c65
- 1mo ago Changed · +18 lines cc6dece080f1
- 1mo ago Changed · +42 lines 71c81d01284b
- 1mo ago First seen · 76 lines · 94 tokens per session scan A dd7dd3c56596
memo is a skill published in the GitHub repository rexleimo/aios (56 stars, last pushed today), licensed MIT. It adds 94 tokens to every session and 1,596 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
memory
Neural memory operations: search stored lessons, store new lessons, inspect memory stats, consolidate episodic patterns, and run decay/pruning.
ai-history
Search and browse AI coding assistant chat history across providers (Claude Code, Codex CLI, Cursor). Find past conversations, inject historical context into the current session, and search across all chat records. Powered by the ai-history CLI tool.
ai-history
Search and browse AI coding assistant chat history across providers (Claude Code, Codex CLI, Cursor). Find past conversations, inject historical context into the current session, and search across all chat records. Use when asked to find past conversations, load context from previous sessions, or search chat history.
opencli-usage
Discover and invoke OpenCLI capabilities for websites and Chrome. Find commands, inspect schemas, interpret results and choose browser or adapter tools.
wttr-weather
Weather via wttr.in GET (no key). Use for weather/forecast; prefer os.http.request.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.