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/gf-labs/claude-toolbox/briefgit clone --depth 1 https://github.com/gf-labs/claude-toolboxWrote 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/gf-labs/claude-toolbox/brief)<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>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 | $0.00052 | $0.03309 |
| Opus 5 | $0.00026 | $0.01655 |
| Sonnet 5 | $0.00010 | $0.00662 |
| Haiku 4.5 | $0.00005 | $0.00331 |
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() 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"
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.
- 5d ago First seen · 328 lines · 52 tokens per session scan B 4b7474d0fa00
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.
Other commands, from other repositories
resume
Resume a previous session. Reads recent session logs, open tasks, and last decisions — gives Claude full context without re-explaining the project.
context-stats
Show context window usage, active tier, and system stats.
explore
Fast codebase exploration with Antigravity's agy CLI (Gemini 3.7 Flash, read-only). EXPERIMENTAL.
result
Show the stored final output for a finished multi-CLI job in this repository.
notebook-status
Check the progress of a /agy:notebook sweep (for long document sets run with --background). Reports % complete, done/pending/failed counts, elapsed time and a rough ETA, and which documents are still pending — so you can resume. Read-only, no agy.
develop
Implement skill development issues with TDD-governed workflow.