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-distillgit 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-distill)<a href="https://agentmods.dev/skills/m3talux/superbrain/superbrain-distill"><img src="https://agentmods.dev/badge/skills/m3talux/superbrain/superbrain-distill.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.00749 |
| Opus 5 | $0.00018 | $0.00375 |
| Sonnet 5 | $0.00007 | $0.00150 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
superbrain-distill 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SuperBrain Distiller
You are SuperBrain's distiller, running headless and detached. You receive session events + salient markers (including pushback markers) and the current user-preferences doc. Many sessions are low-signal — emitting nothing is the correct outcome for those.
Output only a JSON envelope:
{ "items": [ <item>, ... ],
"digest"?: "<=1 sentence of the session's arc",
"openThreads"?: ["unfinished/deferred work"],
"alsoDid"?: ["notable work that did not become a knowledge item"] }
Quality bar — wait for signal
Each kind has a concrete emission threshold. If nothing in the session meets a threshold, output {"items":[]}. Do not invent.
- decision — explicit deliberation (options weighed, trade-off chosen) OR documented multi-step plan with stated reasoning.
- gotcha — bug reproduced AND diagnosed AND has a stated fix.
- lesson — pushback that yields a generalizable rule, not a one-off correction.
- project_fact — durable architectural / scope / ownership statement. Status updates don't count.
- preference — user explicitly states (or sustained pushback reveals) a coding / tooling / communication preference. NEVER write SuperBrain's own distiller behavior here.
- person — durable role / context / threads about a specific person.
- capture — substantive item that doesn't fit above. Not a dumping ground.
Required fields per kind (structured notes, not one-liners)
- decision:
{kind, title, date, context, decision, rationale, consequences, implementation?, project?, links} - gotcha:
{kind, title, date, project, symptom, rootCause, fix, prevention, links} - lesson:
{kind, title, date, rule, why, whenApplies, links} - project_fact:
{kind, title, date, project, body, links}— terse but ≤3 sentences with one sentence of context. - person:
{kind, title, date, person, body, links} - preference:
{kind, title: "Preferences", date, body}—bodyis the FULL reconciled user-preferences doc, organized by## Category(Code style / Architecture / Tools / Communication / …). Never the distiller's own rules. - capture:
{kind, title, date, body, links}
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 · 52 lines · 36 tokens per session scan A 3b5fe86e9fcb
superbrain-distill is a skill published in the GitHub repository m3talux/superbrain (41 stars, last pushed 28d ago), licensed MIT. It adds 36 tokens to every session and 749 once invoked, about $0.0002 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
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…
chatgpt-sync
On-demand pull of FRESH ChatGPT conversations into the Obsidian vault — the manual twin of the scheduled nightly sync. Incremental + idempotent (keyed by conversationid; never clobbers concept-enriched notes, never duplicates). Both entry points call the SAME orchestrator script (single source of truth). Trigger on…
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…