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/savegit clone --depth 1 https://github.com/superuser-pal/awesome-second-brainWhat 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 | $0.00033 | $0.00522 |
| Opus 5 | $0.00016 | $0.00261 |
| Sonnet 5 | $0.00007 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
save 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 2d 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
Process the following input and save it to the vault.
Routing note: Content saved to domains/[Name]/02_PAGES/ or work/04_PAGES/ becomes a permanent page. Content saved to thinking/ is a temporary note with status: thinking (promote via /process when ready).
-
Read the content — understand what the user is sharing. Don't over-interpret or add structure that isn't there.
-
Give it order — clean up the content so it's readable and well-organized:
- Fix obvious typos and formatting issues
- Add light structure (headings, bullets) where it helps readability
- Preserve the user's voice and phrasing — don't rewrite into formal language
- Tag with observation categories (
[fact],[decision],[action], etc.) only where they naturally fit
-
Classify it: decision, incident, 1-on-1 content, win/achievement, architecture, project update, person context, or general work note.
-
Search first: Use
qmd vsearch(orobsidian searchif QMD unavailable) to check if a related note already exists. Prefer appending to existing notes over creating new ones for small updates. -
Create or update the appropriate note following CLAUDE.md conventions:
- Correct folder placement (work/01_PROJECTS/, work/03_INCIDENTS/, work/02_1-1/, work/06_ORG/PEOPLE.md, domains/[Name]/02_PAGES/, etc.)
- Full YAML frontmatter with date, description, tags, and type-specific fields
- All relevant [[wikilinks]] to people, projects, teams, competencies
-
Update indexes as needed (work/INDEX.md, work/05_REVIEW/WINS.md, work/06_ORG/PEOPLE.md)
-
Cross-link: Ensure every new page links to at least one existing page or note and is linked FROM at least one existing page.
After processing, provide a brief summary:
- What was captured and where
- Any notes created or updated (with paths)
- Any items you weren't sure how to classify (ask the user)
Content to save: $ARGUMENTS
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.
- 2d ago First seen · 37 lines · 33 tokens per session scan A 02a7b007d2ca
save is a command published in the GitHub repository superuser-pal/awesome-second-brain (14 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 522 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"…