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/eliransu/digital-brain/supnpx skills add eliransu/digital-brain --skill supgit clone --depth 1 https://github.com/eliransu/digital-brainWrote 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/eliransu/digital-brain/sup)<a href="https://agentmods.dev/skills/eliransu/digital-brain/sup"><img src="https://agentmods.dev/badge/skills/eliransu/digital-brain/sup.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 | $0.00119 | $0.01686 |
| Opus 5 | $0.00060 | $0.00843 |
| Sonnet 5 | $0.00024 | $0.00337 |
| Haiku 4.5 | $0.00012 | $0.00169 |
Grade A, and why
sup 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 5d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sup: Vault-Only Top-10 Dashboard
/sup is fast because it does NOT live-query anything. It reads the markdown files that /digital-brain:sync already wrote into the daily vault folder and renders a Top-10 table.
Strict contract:
- No MCP calls. Not Gmail. Not Slack. Not Linear. Not Calendar. Not Notion. If you find yourself reaching for an MCP tool from
/sup, stop — that is a/syncjob. - Read-only. No writes to
wiki/. - Vault is the source of truth. If the vault doesn't have the data, say so and tell the user to run
/digital-brain:sync.
User identity: [email protected].
Workflow
-
Resolve today's folder.
today = date +%Y-%m-%d(local time). Path:wiki/daily/<today>/. -
Check freshness.
- If the folder doesn't exist → print:
no vault data for today — run /digital-brain:syncand stop. - If the folder exists but the most recent
## Update HH:MM(or top-of-file timestamp) is more than 4 hours old → print the dashboard anyway, but prepend a note:_⚠️ data is <N>h old — consider /digital-brain:sync_.
- If the folder doesn't exist → print:
-
Read all five files in parallel:
mentions.md,topics.md,linear.md,calendar.md,notes.mdfromwiki/daily/<today>/. Ifnotes.mdis missing (older sync), fall back to globbingwiki/notes/*.mddirectly. In-memory filter, no writes: drop any note row whose source file hasstatus: expiredorstatus: done, OR whoseexpires < today(defensive — the file may not have been swept yet). The actualstatusflip lives in/noteand/sync. (Optionally also peek at the prior day's folder if a Slack DM thread spans the boundary — but only if needed to fill the table.) -
Score and rank. Apply the Top-10 selection rules below. Build the table.
-
Render. Output the dashboard. End with a one-line next move.
Top-10 selection rules
| Row earns its spot when… | Skip when… |
|---|---|
| Explicit ask of you (question, review request, decision needed) | Reaction emoji, "ok"/"thanks"/"got it", Spotify links, banter |
| Hard deadline in the next 4h (Calendar event or "by HH:MM" in message) | Calendar invitation / accepted / declined / updated emails |
| Linear issue assigned to you with priority Urgent or High | [email protected], [email protected], |
| Linear mention in a comment within the last 48h | [email protected], AWS marketing |
who-does-what row where the assignee is stalled (>3 days no activity) |
Linear-bot Slack messages that mirror an you message |
| Trip / travel / planning email needing a reply | Pure FYI announcements ("X accepted the invite") |
Note kind: task with status: open (always earns a row) |
Notes with status: expired / done, or expires < today |
Note kind: reminder with due ≤ now + 24h |
Reminders with due > now + 24h (those stay in notes.md but skip the table) |
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.
- 5d ago First seen · 108 lines · 119 tokens per session scan A 07c8a14566cd
sup is a skill published in the GitHub repository eliransu/digital-brain (1 stars, last pushed 3mo ago), licensed MIT. It adds 119 tokens to every session and 1,686 once invoked, about $0.0006 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
llm-wiki
Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or…
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
migrate
Scan the project and migrate existing documentation into OKF format. Use when the user wants to populate the knowledge base from existing docs, README, schemas, API specs, runbooks, or any structured project knowledge. Trigger on "migrate to okf", "populate the knowledge base", "scan my docs", "convert docs to okf"…
architect
Research-backed evolution advice for your knowledge system. Analyzes health reports, friction patterns, and derivation history to propose specific changes with research justification. Never auto-implements — proposals require your approval.
ask
Query the bundled research knowledge graph for methodology guidance. Routes questions through a 3-tier knowledge base — WHY (research claims), HOW (guidance docs), WHAT IT LOOKS LIKE (domain examples) — plus structured reference documents. Returns research-backed answers grounded in specific claims with practical…
fec-nuxt-project-standard
用于创建或审查 Nuxt 3 项目、文件路由、pages、layouts、SSR/SSG/SPA 行为、Nuxt 数据获取、route middleware、plugins、modules、server routes 或 Nuxt 特定 Vue 3 约定。通用 Vue 组件架构另按项目 Vue 约定处理；中文触发词包括 Nuxt、Nuxt 3。.