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 commands/superuser-pal/awesome-second-brain/distributegit clone --depth 1 https://github.com/superuser-pal/awesome-second-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/commands/superuser-pal/awesome-second-brain/distribute)<a href="https://agentmods.dev/commands/superuser-pal/awesome-second-brain/distribute"><img src="https://agentmods.dev/badge/commands/superuser-pal/awesome-second-brain/distribute.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 | $0.00037 | $0.02399 |
| Opus 5 | $0.00018 | $0.01200 |
| Sonnet 5 | $0.00007 | $0.00480 |
| Haiku 4.5 | $0.00004 | $0.00240 |
Grade A, and why
distribute 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Promote all processed notes to their final locations as permanent pages.
Sources to scan (both):
inbox/ready/— all.mdfilesthinking/—.mdfiles withstatus: readyonly (excludethinking/archive/andthinking/README.md)
For each .md file found in the above sources:
1a. Route thinking notes — If a file in inbox/ready/ has status: thinking, move it to thinking/[YYYY-MM-DD]-[name].md and skip it from distribution.
-
Read frontmatter — Extract
domain,type,name, andprojectfields. -
Validate domain exists — Check that
domains/[domain]/exists. If domain is missing ordomain: work(cross-domain), route towork/04_PAGES/instead. If domain does not exist and is not "work", ask user to create it first.Use the user context loaded at session start (from USER.md) to determine whether ambiguous content is work-related vs domain-specific. If content is professional/work-related and no domain clearly fits, offer
work/04_PAGES/as the default. -
Determine destination:
- Default:
domains/[domain]/02_PAGES/(orwork/04_PAGES/for cross-domain content) - If
typeis belief, frame, lesson, model, or goal and the domain has relevant memory files: offer to append to existing memory file instead of creating a new page - If
projectfield is set: link from the project file after placement - If
type: 1-1: route towork/02_1-1/using the per-person accumulating pattern — see step 3a below. - For domain pages: apply steps 3b and 3c to assign a navigation type and sub-folder route.
3b. Assign navigation
typefrom content analysisIf the note is routing to a domain (not
work/), assign one of the six navigation type values by content analysis:Signals type"we decided", rationale, trade-offs, outcome decisionreference material, external source, processed URL sourceidea, framework, mental model, definition conceptAI brief, synthesis, session output, generated report outputfiled question, answered query, Q&A questionaudit, analysis, health check, status report reportIf the note already has a valid navigation type set by
/process, use it (the AI may refine it if the content analysis strongly suggests otherwise). Non-navigation types (goal | plan | research | idea | meeting) pass through unchanged and land flat in02_PAGES/.3c. Route to typed sub-folder (if exists)
Map the assigned
typeto its plural folder name:typeSub-folder conceptconcepts/sourcesources/decisiondecisions/outputoutputs/questionquestions/reportreports/- If
domains/[domain]/02_PAGES/{type_plural}/exists → route there. - If it does not exist → land flat in
domains/[domain]/02_PAGES/(sub-folder emerges later via/auditcluster detection). - Non-navigation types always land flat in
02_PAGES/.
3a. 1:1 routing (accumulating file pattern)
1-1 notes do NOT create a new file per meeting. Instead:
a. Extract
personfield from frontmatter (e.g.,"Babis Pagonis"). b. Check ifwork/02_1-1/[Person].mdalready exists. c. If the file exists — absorb mode:- Extract the meeting date and topic from the note content
- Prepend a new
### [date] — [topic]section immediately after## Meetingsheading - Update
## Latest Summarywith the new meeting context - Update the
datefrontmatter field to the new meeting date - Update
descriptionfrontmatter with a fresh ~150-char rolling summary - Mark source note
status: processed - Archive source to
brain/MASTER_ARCHIVE/and log tobrain/INGEST_LOG.mdwith destination[[work/02_1-1/[Person]|[Person]]] ([date] section) - Skip the file-move steps (file already exists at destination) d. If the file does not exist — create mode:
- Create
work/02_1-1/[Person].mdusing the 1:1 Note schema from ASSET-CLASSES.md - Structure:
## Latest Summary+## Meetingswith the first### [date] — [topic]section +## Relatedwith PEOPLE.md wikilink - Proceed with normal archive + log steps
- Default:
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 · 187 lines · 37 tokens per session scan A 2d80b243e744
distribute is a command published in the GitHub repository superuser-pal/awesome-second-brain (14 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 2,399 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 commands, from other repositories
canvas
AI-orchestrated visual canvas production — create, populate, layout, present, generate, and export Obsidian canvases.
ingest
Ingest a source (URL/file/text) into Raw Sources + compile 1015 Wiki pages, with mandatory user-purpose gate and mothership cross-linking.
lint
Run comprehensive wiki health check — orphans, broken links, contradictions, stale pages, index sync, MOC coverage, v2/v4/v5 frontmatter coverage, Core Context freshness, and cross-vault link integrity (mainVaultRelated/mainVaultCmds).
capture-tabs
Capture a Chrome research tab group or AI-chat research session into LLM Wiki Inbox markdown, then optionally route it through /inbox or /ingest.
om-tidy
Self-maintenance pass — acts on every hygiene flag: archives completed work, groups loose clusters, splits oversized notes, reports stale open loops, fixes links. Safe by construction: never deletes, never commits, zero content loss.
om-incident-capture
Capture an incident from Slack channels, DMs, and threads into structured vault notes. Produces a complete incident work note with timeline, people, analysis, and brag doc entry.