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.
git 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/search-sessions)<a href="https://agentmods.dev/commands/gf-labs/claude-toolbox/search-sessions"><img src="https://agentmods.dev/badge/commands/gf-labs/claude-toolbox/search-sessions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/gf-labs/claude-toolbox/search-sessions"><img src="https://agentmods.dev/badge/commands/gf-labs/claude-toolbox/search-sessions.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00013 | $0.00858 |
| Opus 5 | $0.00006 | $0.00429 |
| Sonnet 5 | $0.00003 | $0.00172 |
| Haiku 4.5 | $0.00001 | $0.00086 |
Grade A, and why
search-sessions 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.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments
$ARGUMENTS
Parse from arguments:
- Positional pattern (any word not starting with
--) — required. Case-insensitive substring match against session title, first user message, and last-prompt content. --days N— limit search to sessions from the last N days (default: no limit)
If no pattern is provided: say "Usage: /tools:search-sessions [--days N]" and stop.
Your role
Read-only session search. Find matching sessions and display them — no deletion.
Step 1 — Search:
python3 -c "
import json, os, sys
from pathlib import Path
from datetime import datetime, timedelta
sys.path.insert(0, os.environ.get('CLAUDE_TOOLBOX_ROOT', '') + '/scripts')
from _projects import iter_session_dirs
args = 'ARGUMENTS_PLACEHOLDER'.split()
pattern = ''
days = None
i = 0
while i < len(args):
if args[i] == '--days' and i + 1 < len(args):
days = int(args[i+1]); i += 2
else:
pattern += (' ' if pattern else '') + args[i]; i += 1
pattern = pattern.lower()
cutoff = (datetime.now() - timedelta(days=days)).timestamp() if days else 0
results = []
try:
_dirs = iter_session_dirs()
except Exception:
_dirs = iter_session_dirs(scope=('global', None, Path.cwd()))
for _key, proj_dir in _dirs:
for f in sorted(proj_dir.glob('*.jsonl')):
if days and f.stat().st_mtime < cutoff: continue
try:
custom_title = first_user = last_prompt = ''
for line in f.read_text(errors='replace').splitlines():
if not line.strip(): continue
obj = json.loads(line)
t = obj.get('type', '')
if t == 'custom-title':
custom_title = obj.get('customTitle', '')
if t == 'last-prompt' and not last_prompt:
last_prompt = obj.get('lastPrompt', '')[:120]
if t == 'user' and not first_user:
msg = obj.get('message', {})
content = msg.get('content', '')
if isinstance(content, list):
for c in content:
if isinstance(c, dict) and c.get('type') == 'text':
first_user = c.get('text', '')[:120]; break
elif isinstance(content, str):
first_user = content[:120]
searchable = (custom_title + ' ' + first_user + ' ' + last_prompt).lower()
if pattern in searchable:
from datetime import date
age_days = (datetime.now().timestamp() - f.stat().st_mtime) / 86400
print(f'MATCH|{_key}|{f.stem[:8]}|{int(age_days)}d|{f.stat().st_size//1024}K|{custom_title or \"(untitled)\"}|{first_user[:80]}')
except Exception:
pass
"
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 · 101 lines · 13 tokens per session scan A 3b00b1838583
search-sessions is a command published in the GitHub repository gf-labs/claude-toolbox (2 stars, last pushed 3d ago), licensed MIT. It adds 13 tokens to every session and 858 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.
suggest-automation
A command that reviews recent Git commits and project instructions to find work patterns that happen repeatedly.
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.
follow-up
Review and act on pending reminders. Bare invocation shows all reminders as an indexed list; cron-fired invocation (/follow-up due ) surfaces the specific reminder and waits for a response; /follow-up review lists stale project follow-up entries for per-item disposition (extend/close/promote/skip). Transport-aware…
explore
Fast codebase exploration with Antigravity's agy CLI (Gemini 3.7 Flash, read-only). EXPERIMENTAL.