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/brain-dumpgit 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/brain-dump)<a href="https://agentmods.dev/commands/superuser-pal/awesome-second-brain/brain-dump"><img src="https://agentmods.dev/badge/commands/superuser-pal/awesome-second-brain/brain-dump.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 | $0.00032 | $0.00784 |
| Opus 5 | $0.00016 | $0.00392 |
| Sonnet 5 | $0.00006 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
brain-dump 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 4d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brain Dump
"What's on your mind? Share your thoughts freely."
Usage
/brain-dump <content>
This command is designed for deeper reflection and stream-of-consciousness capture. It extracts atomic observations and stages them in inbox/raw/.
Workflow
1. Collect Raw Input
Accept any format:
- Stream of consciousness
- Voice-to-text output
- Bullet points
- Rambling paragraphs
No filtering, no judgment — capture everything exactly as provided.
2. Content Analysis
Internal analysis (not written to file):
- Main Themes: [3-5 primary topics]
- Supporting Ideas: [related concepts]
- Action Items: [tasks identified if any]
3. Observation Extraction
Extract atomic observations from the raw content, categorizing each.
Process:
- Identify distinct statements in the raw input.
- For each statement, determine the most appropriate category:
fact,idea,decision,technique,requirement,question,insight,problem,solution,action. - Format as structured observations:
- [category] content #tag1 #tag2. - Suggest 2-3 relevant tags per observation (AI-suggested based on context).
Rules:
- Each observation must be atomic (single subject-verb-object).
- Present extractions to the user for confirmation if they are complex.
4. Domain and Theme Detection
Analyze content to detect target domain and themes.
- Segment content by topic shifts (paragraph breaks, explicit markers like "Also...", domain changes).
- Determine if the content should be split into multiple raw notes.
Multi-note detection: if content contains 3 or more distinct topics that are each independently note-worthy (self-contained, useful on their own), offer to split before writing any files.
Present a split preview:
Detected 3 distinct topics — each could be its own raw note:
1. [Topic A] (domain: X, suggested type: concept) → inbox/raw/topic-a-YYYY-MM-DD.md
2. [Topic B] (domain: Y, suggested type: decision) → inbox/raw/topic-b-YYYY-MM-DD.md
3. [Topic C] (domain: X, suggested type: idea) → inbox/raw/topic-c-YYYY-MM-DD.md
Options:
a) Create 3 separate raw notes (recommended)
b) Capture as a single note
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.
- 4d ago First seen · 90 lines · 32 tokens per session scan A 556581d1bc28
brain-dump is a command published in the GitHub repository superuser-pal/awesome-second-brain (14 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 784 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.
audit
Audit the whole Wiki vault against 3 knowledge-integrity criteria — eligibility coverage, MOC-cluster consistency, confidence calibration. Produces a vault health report and queues high-priority pages for /verify.
verify
Verify a single Wiki page against 3 knowledge-integrity criteria — eligibility, consistency, confirmability. Writes verificationStatus back to the page; flags conflicts as disputed rather than deleting them.
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).
onboard
Interview-based first-run setup for this LLM Wiki kit. Asks the essential questions (vault location/name, Mode A/B, mothership path, Core Context identity + reuse axes), then fills every placeholder and writes Core Context so the wiki knows you from day one. Activate when the user says "온보딩해줘", "처음 시작할게", "처음 시작"…