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/wrapgit 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/wrap)<a href="https://agentmods.dev/commands/gf-labs/claude-toolbox/wrap"><img src="https://agentmods.dev/badge/commands/gf-labs/claude-toolbox/wrap.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 | $0.00046 | $0.02418 |
| Opus 5 | $0.00023 | $0.01209 |
| Sonnet 5 | $0.00009 | $0.00484 |
| Haiku 4.5 | $0.00005 | $0.00242 |
Grade A, and why
wrap scanned grade A with 1 finding 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.
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 — 254 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 proceeding. Store results mentally.
Scope:
python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/_scope.py
Session activity:
python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/collect-summarize.py
Session log status:
python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/collect-session-log.py
session-log.md (full content, for skip check):
python3 -c "
import os, sys
sys.path.insert(0, os.environ.get('CLAUDE_TOOLBOX_ROOT', '') + '/scripts')
from _scope import get_scope, project_key
from pathlib import Path
mode, data, cwd = get_scope()
projects_dir = Path.home() / '.claude' / 'projects'
if mode == 'single':
key = data
else:
import subprocess
try:
git_root = subprocess.check_output(['git', 'rev-parse', '--show-toplevel'], stderr=subprocess.DEVNULL, text=True).strip()
key = project_key(git_root, projects_dir)
except Exception:
print('SESSION_LOG: unavailable')
exit(0)
log = projects_dir / key / 'memory' / 'session-log.md'
print(f'PATH: {log}')
print(log.read_text() if log.exists() else 'MISSING — will be created on first save')
"
Git state, diff, unpushed commits, backlog, date:
echo "GIT_DIFF_STAT:" && (git diff HEAD --stat 2>/dev/null || echo "none")
echo "GIT_STATE:" && (git status --short 2>/dev/null || echo "clean")
echo "UNPUSHED:" && (git log @{u}.. --oneline 2>/dev/null || echo "none (or no remote)")
TW_PROJECT=$(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
Plans:
python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/collect-plans.py
Project MEMORY.md:
python3 -c "
import os, sys
sys.path.insert(0, os.environ.get('CLAUDE_TOOLBOX_ROOT', '') + '/scripts')
from _scope import get_scope, project_key
mode, data, cwd = get_scope()
from pathlib import Path
projects_dir = Path.home() / '.claude' / 'projects'
if mode == 'single':
mem = projects_dir / data / 'memory' / 'MEMORY.md'
print(f'PATH: {mem}')
print(mem.read_text() if mem.exists() else 'MISSING')
elif mode == 'parent':
print('PARENT MODE — see scope output for child projects')
else:
import subprocess
git_root = subprocess.check_output(['git', 'rev-parse', '--show-toplevel'], stderr=subprocess.DEVNULL, text=True).strip()
key = project_key(git_root, projects_dir)
mem = projects_dir / key / 'memory' / 'MEMORY.md'
print(f'PATH: {mem}')
print(mem.read_text() if mem.exists() else 'MISSING')
"
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.
- 4d ago First seen · 254 lines · 46 tokens per session scan A 2c28cfc73c3e
wrap is a command published in the GitHub repository gf-labs/claude-toolbox (2 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 2,418 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (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
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
save
Save this conversation as a new or existing reusable context.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
wp-polylang
Translate an existing WordPress site into a second language using Polylang.