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/m3talux/superbrain/injectgit clone --depth 1 https://github.com/m3talux/superbrainWhat 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 | $0.00123 | $0.00824 |
| Opus 5 | $0.00062 | $0.00412 |
| Sonnet 5 | $0.00025 | $0.00165 |
| Haiku 4.5 | $0.00012 | $0.00082 |
Grade A, and why
inject 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 3d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/superbrain:inject
Manual ingestion path. Auto-capture remains the default — this is for content SuperBrain can't observe.
What it does
- Validates input (non-empty, alphanumeric, ≤32 KB).
- Auto-detects mode: verbatim for ≤200 chars with no blank-line separator; distill otherwise. Flags
--verbatim/--distilloverride. - Verbatim: writes a single
capture/<date>-<slug>.md(orprojects/<slug>.mdappend if--projectis passed). No LLM call. - Distill: pulls top-5 related vault notes via recall, lists existing project slugs, calls Sonnet 4.6 with the inject-specific prompt, parses the envelope, routes each item via the same
route()the session distiller uses. - Updates today's daily note. Logs to
~/.superbrain/inject.log. - On LLM failure or empty envelope, falls back to verbatim capture — input is never lost.
Safety rails
- Inject NEVER creates a new project note. Unknown project slugs are downgraded to
capture/. (Project notes are created only by/superbrain:discover.) - Inject NEVER reshapes preferences. Preference items emitted by the model are dropped.
--project <slug>always wins over anything the model emits.- Concurrent with an active session checkpoint? Inject takes the same lock and waits up to 5 s.
How to invoke
Step 1 — gather the user's text. The slash command argument string is in $ARGUMENTS. If $ARGUMENTS is empty, ask the user what they'd like to inject before running the command.
Step 2 — invoke the CLI. Pass the argument string straight through; the CLI parses flags itself.
node "${CLAUDE_PLUGIN_ROOT}/dist/bin/sb-inject.js" $ARGUMENTS
If the user wants to inject the contents of a file (e.g. a meeting summary they pasted into ~/Downloads/meeting.md), use --from-file:
node "${CLAUDE_PLUGIN_ROOT}/dist/bin/sb-inject.js" --from-file "<path>"
Step 3 — when the call returns, surface the output verbatim (it lists the rel paths of every note written) so the user knows where each piece landed.
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.
- 3d ago First seen · 55 lines · 0 tokens per session scan A 078b4677d306
inject is a command published in the GitHub repository m3talux/superbrain (41 stars, last pushed 22d ago), licensed MIT. It adds 123 tokens to every session and 824 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 2026-08-30.
Other commands, from other repositories
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.
om-capture-1on1
Take a meeting transcript, notes, or Gemini summary and create a structured vault note with key takeaways, quotes, action items, and DM context.
om-weekly
Weekly synthesis — cross-session review of vault activity, North Star alignment, patterns, uncaptured wins, and forward priorities.
om-dump
Freeform capture mode. Dump anything — conversations, decisions, incidents, wins, thoughts — and I'll route it all to the right notes with proper templates, frontmatter, and wikilinks.
okf
Command "okf" from kimsanguine/llm-brain, covering 인자 파싱, 기본 private export, 🔴 share-ready gate (외부 공유 전 one-way door), legacy step 1: private dry-run 검토 and legacy step 2: private export.
pdf-to-wiki
Drive에 있는 대용량 PDF를 NotebookLM에 외주화하여 분석하고, 결과를 OUTPUTDIR에 Obsidian 노트로 저장한다.