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.
/plugin marketplace add tigerquoll/claude-brief/plugin install claude-briefWrote 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.
[](https://agentmods.dev/commands/tigerquoll/claude-brief/brief)<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
- 8d ago First seen · 32 lines · 14 tokens per session scan A 5d70b57c7c88
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.
Other commands, from other repositories
aside
Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.
evolve
Cluster related instincts into skills, commands, or agents.
suggest-automation
A command that reviews recent Git commits and project instructions to find work patterns that happen repeatedly.
instinct-import
Import instincts from teammates, Skill Creator, or other sources.
instinct-export
Export instincts for sharing with teammates or other projects.
atomic-help
Route a lost user to the right atomic verb, skill, agent, or binary subcommand. Bare invocation reads git state and recommends one next step. Topic keyword or freeform intent → focused pointer. tour → guided walkthrough of the system. Help router, not duplicated docs.