brief

brief is a command for Claude Code from tigerquoll/claude-brief. It costs 14 tokens per session (517 once invoked), scanned A, original, BSD-3-Clause.

A command that opens or focuses the docked pane containing the current session's live summary. A docked pane is a side-by-side terminal area next to the main session.

In plain words
What is it for?
It can refresh, close, or show help for the summary pane, and lets you change automatic or periodic refresh settings.
Why use it?
It gives quick access to the session summary without manually finding or opening the pane.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude-brief plugin — 1 command, 4 hooks shipped together

Good fit It can refresh, close, or show help for the summary pane, and lets you change automatic or periodic refresh settings.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add tigerquoll/claude-brief
Claude Code
/plugin install claude-brief

Made for: Claude Code.

Or install claude-brief, the plugin that ships this one along with the rest of its 1 command, 4 hooks.

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/tigerquoll/claude-brief/brief.svg)](https://agentmods.dev/commands/tigerquoll/claude-brief/brief)
Your own site
<a href="https://agentmods.dev/commands/tigerquoll/claude-brief/brief"><img src="https://agentmods.dev/badge/commands/tigerquoll/claude-brief/brief.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 517 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00014 $0.00517
Opus 5 $0.00007 $0.00259
Sonnet 5 $0.00003 $0.00103
Haiku 4.5 $0.00001 $0.00052

Measured 8d ago against content hash 5d70b57c7c88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

commands/brief.md · 32 lines

What it actually says

This session's running brief (state · what's been tried · gotchas · decisions · next) is shown in a docked pane — a side-by-side split (or, on Apple Terminal, a companion window beside this one), opened or re-focused just now. The terminal backend is auto-detected (iTerm2 / tmux / kitty / ghostty / Apple Terminal). Click the dock pane to use its keys: r refresh now · a toggle auto (refresh at the end of each turn — the default; turn off for on-demand only) · i toggle interval (refresh periodically during a long turn; only fires on new activity, so idle never spends) · +/- set the interval period (30s–1h) · ? key help · q close. The footer shows both modes. The brief is sized to fit the dock pane. /brief refresh does a one-shot refresh from here but re-splits the pane. /brief close tears the dock down (a clean, no-prompt close on every backend — preferred over q/⌘W, which on ghostty leave an empty pane / pop a confirm). /brief help prints the usage, in-dock keys, and docs pointers without touching the dock. /brief debug prints a sanitised diagnostic report (no env values, no brief/transcript content — safe to paste into a GitHub issue) and runs one tiny probe summary call.

!"${CLAUDE_PLUGIN_ROOT}/bin/brief-open.sh" $ARGUMENTS

If the argument was help or debug, reproduce the command output above verbatim in a fenced code block — that output IS the answer (for debug, you may add a short diagnosis of what the report shows after the block). Otherwise acknowledge in ONE short line that the brief dock is up — and if the output includes a "brief: first dock" hint line, relay that hint too (it appears once, ever) — or, if the command above reported an error, relay that error. Do NOT reproduce the brief here.

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. 8d ago First seen · 32 lines · 14 tokens per session scan A 5d70b57c7c88

Subscribe to this mod's changes

brief is a command published in the GitHub repository tigerquoll/claude-brief (5 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 14 tokens to every session and 517 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.