brief

brief is a command for Claude Code from gf-labs/claude-toolbox. It costs 52 tokens per session (3,309 once invoked), scanned B, original, MIT.

A command for orienting a fresh or long-idle Claude Code session by collecting project scope, status, and the point where work stopped.

In plain words
What is it for?
Use it at the start of a new session or after an absence lasting days or weeks.
Why use it?
It reduces the time spent reconstructing context after returning to a project.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md.

Part of the tools plugin — 2 skills, 13 commands, 5 agents, 4 hooks shipped together

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/gf-labs/claude-toolbox/brief
Clone the repo
git clone --depth 1 https://github.com/gf-labs/claude-toolbox

Made for: Claude Code.

Or install tools, the plugin that ships this one along with the rest of its 2 skills, 13 commands, 5 agents, 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/gf-labs/claude-toolbox/brief.svg)](https://agentmods.dev/commands/gf-labs/claude-toolbox/brief)
Your own site
<a href="https://agentmods.dev/commands/gf-labs/claude-toolbox/brief"><img src="https://agentmods.dev/badge/commands/gf-labs/claude-toolbox/brief.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,309 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 5.1 $0.00052 $0.03309
Opus 5 $0.00026 $0.01655
Sonnet 5 $0.00010 $0.00662
Haiku 4.5 $0.00005 $0.00331

Measured 5d ago against content hash 4b7474d0fa00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

brief scanned grade B with 2 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 5d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat .claude/status.md 2>/dev/null || echo "(no project extension)"

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

git_root = subprocess.check_output(['git', 'rev-parse', '--show-toplevel'], stderr=subprocess.DEVNULL, text=True).strip()
commands/brief.md · 328 lines

How it starts

The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Collect context

Run each command below now before producing output. Store results mentally.

Scope:

python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/_scope.py

Status:

python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/collect-status.py

Absence duration + resume point:

python3 -c "
import os, re, sys
from datetime import datetime
from pathlib import Path
sys.path.insert(0, os.environ.get('CLAUDE_TOOLBOX_ROOT', '') + '/scripts')
from _scope import get_scope, project_key
mode, data, cwd = get_scope()
projects_dir = Path.home() / '.claude' / 'projects'
if mode == 'single':
    key = data
else:
    import subprocess
    try:
        git_root = subprocess.check_output(['git', 'rev-parse', '--show-toplevel'], stderr=subprocess.DEVNULL, text=True).strip()
        key = project_key(git_root, projects_dir)
    except Exception:
        print('ABSENCE_DAYS: unknown')
        sys.exit(0)
log = projects_dir / key / 'memory' / 'session-log.md'
if not log.exists():
    print('ABSENCE_DAYS: unknown')
    sys.exit(0)
text = log.read_text()
dates = re.findall(r'^## (\d{4}-\d{2}-\d{2})', text, re.MULTILINE)
if not dates:
    print('ABSENCE_DAYS: unknown')
    sys.exit(0)
last = max(dates)
delta = (datetime.today().date() - datetime.strptime(last, '%Y-%m-%d').date()).days
print(f'ABSENCE_DAYS: {delta}')
print(f'LAST_SESSION_DATE: {last}')
blocks = re.split(r'(?=^## \d{4}-\d{2}-\d{2})', text, flags=re.MULTILINE)
dated = [b for b in blocks if re.match(r'^## \d{4}-\d{2}-\d{2}', b)]
last_block = sorted(dated, key=lambda b: re.match(r'^## (\d{4}-\d{2}-\d{2})', b).group(1))[-1] if dated else ''
resume = re.search(r'^\*\*Resume:\*\* (.+)$', last_block, re.MULTILINE)
print(f'RESUME: {resume.group(1)}' if resume else 'RESUME: (none)')
"

Session log (metadata + recent entries — depth scales to absence):

python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/collect-session-log.py

Plans (with first bullet):

python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/collect-plans.py

Plan map (project associations):

python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/collect-plan-map.py

Branch, changes, commits, stash, CLAUDE.md, backlog, date:

echo "BRANCH:" && (git branch -vv 2>/dev/null | grep '^\*' || echo "not a git repo")
echo "CHANGES:" && (git status --short 2>/dev/null || echo "clean")
echo "COMMITS:" && (git log --oneline -5 2>/dev/null || echo "none")
echo "STASH:" && (git stash list 2>/dev/null || echo "empty")
echo "CLAUDE_MD:" && (test -f CLAUDE.md && echo "present" || echo "MISSING")
TW_PROJECT=$(python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/_slug.py)
echo "IN_PROGRESS:" && (task rc.verbose=nothing project:${TW_PROJECT} +ACTIVE list 2>/dev/null || echo "(none)")
echo "UP_NEXT:" && (task rc.verbose=nothing project:${TW_PROJECT} limit:3 list 2>/dev/null || echo "(none)")
echo "DATE:" && date +%Y-%m-%d

Current session:

python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/collect-summarize.py

Recent Claude activity:

python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/collect-history.py $ARGUMENTS

Ramp — nodes due today:

python3 -c "
import re
from datetime import date
from pathlib import Path
today = date.today().isoformat()
g = Path.home() / '.claude' / 'knowledge-graphs' / 'claude-code.md'
if not g.exists():
    print('no graph')
else:
    text = g.read_text()
    due = [m for m in re.findall(r'next: (\d{4}-\d{2}-\d{2})', text) if m <= today]
    level_match = re.search(r'^level: (.+)$', text, re.MULTILINE)
    xp_match = re.search(r'^xp: (\d+)$', text, re.MULTILINE)
    level = level_match.group(1) if level_match else '?'
    xp = xp_match.group(1) if xp_match else '?'
    print(f'{len(due)} nodes due  |  {level}  |  {xp} XP')
" 2>/dev/null || echo "no ramp graph"

Phase / roadmap:

python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/collect-phase.py 2>/dev/null || echo "NOT_FOUND"

Toolbox env:

printenv CLAUDE_TOOLBOX_ROOT 2>/dev/null && echo "(set)" || echo "NOT SET"

Read the full file on GitHub · 328 lines

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. 5d ago First seen · 328 lines · 52 tokens per session scan B 4b7474d0fa00

Subscribe to this mod's changes

brief is a command published in the GitHub repository gf-labs/claude-toolbox (2 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 3,309 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.