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 m3talux/superbrain --skill superbrain-recallgit clone --depth 1 https://github.com/m3talux/superbrainWrote 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/m3talux/superbrain/superbrain-recall)<a href="https://agentmods.dev/skills/m3talux/superbrain/superbrain-recall"><img src="https://agentmods.dev/badge/skills/m3talux/superbrain/superbrain-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 5.1 | $0.00056 | $0.00454 |
| Opus 5 | $0.00028 | $0.00227 |
| Sonnet 5 | $0.00011 | $0.00091 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
superbrain-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 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.
What it actually says
SuperBrain Recall
When the user's question may already be answered by their accumulated notes, call the
superbrain_search MCP tool (server superbrain) with a focused query (and optional
k, default 8).
- Lead with what the vault says; cite every claim with the returned
[[wikilink]]. - If results are empty or irrelevant, say so plainly and answer normally — never fabricate a citation or invent a note.
- Prefer one well-formed query over many noisy ones.
Gap sensing — when memory looks stale
Recalled memory can lag reality: a session may have crashed before its last checkpoint distilled, or the machine slept mid-conversation. Before answering questions about recent work, check for staleness signals:
- git history shows commits NEWER than the latest memory for this project
- the user references recent work you have no recall of
When you suspect a gap:
- List
sessions/in the vault, filtered to this project's slug, newest first (the filename embeds a unix timestamp:{project}-{ts}.md). - Read the newest note that is not the current session: the
## Digestline summarizes the session as of its last checkpoint; the## Turn logcarries the raw prompt/reply trail beyond it. - If finer detail is needed and the session is recent (~30 days), the raw
Claude transcript can be derived —
~/.claude/projects/<cwd with "/" and "." replaced by "-">/, newest.jsonlby mtime. Read its tail rather than the whole file. Where resuming would genuinely help, offerclaude --resume <session-id>to the user; never resume on your own. - State plainly which parts of your answer come from the flight recorder versus distilled memory.
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 First seen · 40 lines · 56 tokens per session scan A a5d03d6246a0
superbrain-recall is a skill published in the GitHub repository m3talux/superbrain (41 stars, last pushed 27d ago), licensed MIT. It adds 56 tokens to every session and 454 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 2026-08-30.
Other skills, from other repositories
garden-tending
Tend the knowledge garden — diagnose vault health, condense project memos into project.md overviews, create/merge cross-project topics, fix broken links, archive superseded notes, extend trails. Trigger on "tend the garden", "condense", "update project overview", "check vault health", "where are we with X?", "what…
curator-practice
Operating philosophy for autonomous memex curator tending — orientation protocol, signal triage, bounded work units, initiative thresholds, logging conventions. Trigger on cron-launched runs with no user prompt, "use your judgment", "tend without instructions", "do a pass on the vault", "I'll be away — do what needs…
memo-writing
How to write effective session memos — format, frontmatter schema, observation extraction, topic-signal append. Trigger on /memex:save, "save this for later", "remember this", "save what we discussed", "document this session", "create a memo", or when the [memex] activity nudge appears in context. Do NOT trigger for…
recall
Retrieve session memory across 4 modes — TEMPORAL (date browsing), KEYWORD (FTS lookup), DEEP (cross-session synthesis), LOAD (specific file). Trigger on "what did I do yesterday/last week", "why did we...", "remind me...", "find the memo about...", "last time we...", "patterns across projects", "load the X topic". Do…
follower-onboard
Onboard a NEW family/team machine as a FOLLOWER-CONSUMER joining the multi-machine Claude+vault network. A follower READS the shared vault + canon + skills + memory as RECEIVE- ONLY data, runs nothing heavy locally (no RAG/reindex/GPU), and the hub never pushes executable hooks to it. Trigger on "/follower-onboard "…
claudeai-sync
One-command incremental sync of a claude.ai WEB account into the Obsidian vault — pull only new/changed chats, fold them in as notes (idempotent, never overwrites curated ones), extract artifacts as first-class notes, concept-link the new artifacts, refresh the RAG index + dashboard. Trigger on "/claudeai-sync", "pull…