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/railly/agent-brain/inboxgit clone --depth 1 https://github.com/Railly/agent-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 | $0.00014 | $0.01185 |
| Opus 5 | $0.00007 | $0.00593 |
| Sonnet 5 | $0.00003 | $0.00237 |
| Haiku 4.5 | $0.00001 | $0.00119 |
Grade A, and why
inbox 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Process pending clips from 01_Inbox/.
IMPORTANT: Be direct
- Don't check if folders exist - they do
- Don't search for existing notes - just write
- Don't read ideas.md before appending - just append
- Minimize tool calls
Flow
-
Find unprocessed clips List all
.mdfiles directly in01_Inbox/- these are unprocessed. -
For each clip (read content, extract insight, identify topic)
-
Create atomic note in
03_Garden/concepts/{topic-slug}.md(FLAT, evergreen):--- type: concept created: {{date}} themes: [] sources: - "[[01_Inbox/processed/{{date}}/{processed-slug}]]" people: [] --- # {Topic} {1-2 sentence insight} ## Key ideas - {extracted points} ## Connections - [[Related concept]] - how it relatesIf concept already exists: Append to Key ideas + add new source to
sources:array -
Extract content ideas to
05_Areas/content-creation/ideas/{{date}}/{slug}.md:--- type: content-idea format: tweet | thread | blog | short | tutorial status: idea source: "[[03_Garden/concepts/{concept-slug}]]" created: {{date}} priority: 3 --- # {Title} {The content idea - actual tweet text, thread hook, or blog thesis} ## Hook {Why this will resonate} ## Notes - {Additional context} -
Enrich with metadata:
- People: If author or people mentioned, create
03_Garden/people/{person-name}.mdif doesn't exist - Location: If place mentioned, add coordinates to concept note
- People: If author or people mentioned, create
-
Find connections
- List existing notes:
03_Garden/concepts/ - Look for related topics (semantic similarity, shared tags)
- Add backlinks to the new concept and existing related concepts
- List existing notes:
-
Mark clip as processed - add
generated:links + move to date folder:First, update the clip's frontmatter to add the
generated:field:--- generated: - "[[03_Garden/concepts/{concept-slug}]]" - "[[05_Areas/.../ideas/{{date}}/{idea-slug}]]" ---
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 · 138 lines · 14 tokens per session scan A d15ce86973e7
inbox is a command published in the GitHub repository Railly/agent-brain (22 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 1,185 once invoked, about $0.0001 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
learn
Force claude-smart to extract learnings from this session now.
component
Scaffold a new React component grounded in the paper-mono primitives. Requires explicit kind or a nearest-existing-component match. No empty divs, no speculative scaffolding.
memory-store
Store an insight, decision, or pattern to memory.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
no-vibe
Enter no-vibe mode in OpenCode (tutor mode, no direct project file writes).
teach-me-testing
Teach testing progressively through structured sessions. Use when user says ""lets learn testing"" or ""I want to study test practices"".