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/binary16labs/prime-silo/memory-recallnpx skills add binary16labs/prime-silo --skill memory-recallgit clone --depth 1 https://github.com/binary16labs/prime-siloWrote 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/binary16labs/prime-silo/memory-recall)<a href="https://agentmods.dev/skills/binary16labs/prime-silo/memory-recall"><img src="https://agentmods.dev/badge/skills/binary16labs/prime-silo/memory-recall.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 | $0.00070 | $0.00721 |
| Opus 5 | $0.00035 | $0.00360 |
| Sonnet 5 | $0.00014 | $0.00144 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
Memory 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 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.
What it actually says
Use this skill when the user asks about their own history — past sessions, what they were working on, which sessions touched a file, or the lineage of a piece of work. The answers come from the Memo-Ray memory graph, the third graph of the cognitive mesh (beside the knowledge graph and the code graph). You query it; the user should never have to be their own institutional memory.
load helper
await import("/mod/_prime_silo/memoray_client/ext/skills/memory-recall/memory-recall.js")- All calls go through the shell proxy (
/api/memoray); no endpoint configuration needed. - If a call throws "Memo-Ray is offline" or "disabled", relay that to the user with the fix (boot
scripts/memoray.ps1, or enable it in the configuration wizard) — do not retry in a loop.
helpers
recentSessions({ agent?, limit? })->[{ id, title, agent, project, timestamp, link }]search(query)->{ sessions:[{…, link}], files, actions }(omnibar across sessions/files/actions)overview()->{ claude, antigravity, totalNodes, lastSync }ecosystem totalssessionGraph(sessionId)->{ nodes, links }full lineage of one sessionfilesTouched(query)->[{ fileName, filePath, agent }]sessionLink(sessionId)-> deep link string into the visual memory page
guidance
- ALWAYS cite the session id and include the deep link (
link, orsessionLink(id)→#/_prime_silo/memory?session_id=<id>) so the user can open the visual lineage at the memory page. Format as a markdown link to the hash route. - Prefer
search(...)for "which sessions touched X" or fuzzy questions; preferrecentSessions(...)for "what was I working on". - Summarize — don't dump raw JSON. Lead with the answer (e.g. "You last worked on the lineage widget 2 hours ago"), then offer the link.
- This is read-only. You cannot modify the memory graph; you observe it.
examples Recent work
const memory =
await import("/mod/_prime_silo/memoray_client/ext/skills/memory-recall/memory-recall.js");
const sessions = await memory.recentSessions({ limit: 5 });
return sessions;
Which sessions touched a file
const memory =
await import("/mod/_prime_silo/memoray_client/ext/skills/memory-recall/memory-recall.js");
return await memory.search("memoray_proxy.js");
Lineage of a specific session
const memory =
await import("/mod/_prime_silo/memoray_client/ext/skills/memory-recall/memory-recall.js");
const graph = await memory.sessionGraph("<session-id>");
return {
nodes: graph.nodes.length,
links: graph.links.length,
link: memory.sessionLink("<session-id>")
};
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 60 lines · 70 tokens per session scan A e531cd64d249
Memory recall is a skill published in the GitHub repository binary16labs/prime-silo (5 stars, last pushed 10d ago), licensed MIT. It adds 70 tokens to every session and 721 once invoked, about $0.0003 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
draw-image
Generate an image from a text prompt using an OpenAI-compatible image generation API (gpt-image-1-mini or compatible). The image is uploaded to the gofile.io public file sharing service and ONLY the public download page URL is returned. Trigger when user asks to draw, paint, generate, or create an image.
compose:subagent
Use when executing implementation plans with independent tasks in the current session.
compose:worktree
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback.
compose:merge
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup.
compose:new-skill
Use when creating new skills or editing existing skills for the project or personal skill library.
compose:plan
Use when you have a spec or requirements for a multi-step task, before touching code.