brief

brief is a command for Claude Code from slowww-ai/second-brain. It costs 11 tokens per session (319 once invoked), scanned A, original, MIT.

A command for collecting relevant notes from a local wiki and writing them into a structured brief. A brief is a short document that summarizes a topic for a chosen audience.

In plain words
What is it for?
Use it to research a topic from wiki notes and produce a Markdown, DOCX, or PDF brief after confirming the audience, tone, length, and format.
Why use it?
It avoids searching notes manually and organizes the findings, details, open questions, and sources in one output file.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/slowww-ai/second-brain/brief
Clone the repo
git clone --depth 1 https://github.com/slowww-ai/second-brain

Made for: Claude Code.

Wrote 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.

agentmods badge for brief

README.md
[![agentmods](https://agentmods.dev/badge/commands/slowww-ai/second-brain/brief.svg)](https://agentmods.dev/commands/slowww-ai/second-brain/brief)
Your own site
<a href="https://agentmods.dev/commands/slowww-ai/second-brain/brief"><img src="https://agentmods.dev/badge/commands/slowww-ai/second-brain/brief.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 319 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.00319
Opus 5 $0.00005 $0.00160
Sonnet 5 $0.00002 $0.00064
Haiku 4.5 $0.00001 $0.00032

Measured 4d ago against content hash 42bd7fd2610a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brief 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.

.claude/commands/brief.md · 24 lines

What it actually says

Topic: $ARGUMENTS

Your job is to produce a brief on the given topic using only information from wiki/notes/ (and wiki/raw/ for citations when needed).

Steps:

  1. Run python scripts/search.py "<topic keywords>" with several query variations to find relevant notes.
  2. Also try python scripts/search.py --tag <likely-tag> if a tag seems obvious.
  3. Read the top ~10 hits in full. Follow [[wikilinks]] one hop when useful.
  4. Before writing, first ask the user (using AskUserQuestion) to confirm:
    • the intended audience and tone
    • desired length (one-pager, deep dive, etc.)
    • output format (markdown, docx, pdf) — default markdown unless these are already clear from the arguments.
  5. Draft the brief in wiki/outputs/<date>-<slug>.md with sections: TL;DR, Key points, Details, Open questions, Sources.
  6. In "Sources", list the note IDs you used as a bulleted list.
  7. If the user asked for .docx or .pdf, use the appropriate skill to render the final file alongside the markdown.
  8. Share the output file with a computer:// link and a one-sentence summary. Do not restate the whole brief in chat.
Changes

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.

  1. 4d ago First seen · 24 lines · 11 tokens per session scan A 42bd7fd2610a

Subscribe to this mod's changes

brief is a command published in the GitHub repository slowww-ai/second-brain (10 stars, last pushed 21d ago), licensed MIT. It adds 11 tokens to every session and 319 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 2026-08-31.