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 aios-offload-recallgit 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/aios-offload-recall)<a href="https://agentmods.dev/skills/rexleimo/aios/aios-offload-recall"><img src="https://agentmods.dev/badge/skills/rexleimo/aios/aios-offload-recall/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/aios-offload-recall"><img src="https://agentmods.dev/badge/skills/rexleimo/aios/aios-offload-recall.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 | $0.00034 | $0.00438 |
| Opus 5.5 | $0.00014 | $0.00175 |
| Sonnet 5.5 | $0.00007 | $0.00088 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
aios-offload-recall 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.
What it actually says
AIOS Offload Recall
Use this when prior tool output is likely stored under .aios/offload/ and token use matters.
Recall Order
- Identify the session id from ContextDB, harness status, or the user's handoff.
- Run
aios canvas show --session <id>to inspect the compact task graph. - Search narrowly with
aios refs grep "<pattern>" --session <id>. - Read only the needed node with
aios refs read <node_id>. - Summarize the recalled evidence and keep the
node_idin your notes.
Backfill Existing Logs
If a previous run produced JSONL tool-event logs but no canvas yet, create the index first:
aios canvas backfill --input <events.jsonl> --client <client> --session <id>
Then resume the recall order above. Backfill accepts generic records with fields like tool, input, output,
or Claude-style tool_name, tool_input, tool_response.
Rules
- Do not load every ref file unless the user explicitly asks for a full audit.
- Do not treat the canvas as complete evidence; it is an index over raw refs.
- If a node may contain secrets, use
aios privacy read --file <path>before sharing content. - Savings are future-context savings: canvas/node_id replaces raw log replay during resume or recall.
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 Changed 5a117e53ce0d
- 1mo ago Changed 48155fccb5ce
- 1mo ago Changed 257d9c1f3e99
- 1mo ago First seen · 44 lines · 34 tokens per session scan A b9a362a1d36d
aios-offload-recall is a skill published in the GitHub repository rexleimo/aios (61 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 438 once invoked, about $0.0001 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
engram-memory
Give the agent durable, local memory with engram — recall past decisions before answering, and persist new decisions, preferences and facts as they happen. Use when work spans sessions or the user says "remember".
aitask-note
Send a durable note to an existing aitask — context that task needs which is not itself work. Use when you learn something a task that already exists depends on, such as a stale assumption in its body, a wider blast radius, or a decision that changes its approach.
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.