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 skills/valkryhx/google_adk_agent/bashnpx skills add valkryhx/google_adk_agent --skill bashgit clone --depth 1 https://github.com/valkryhx/google_adk_agentWhat 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 | $0.00036 | $0.03033 |
| Opus 5 | $0.00018 | $0.01517 |
| Sonnet 5 | $0.00007 | $0.00607 |
| Haiku 4.5 | $0.00004 | $0.00303 |
Grade C, and why
Bash Tool scanned grade C with 3 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 2d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
1. **禁止执行高危命令**（如 `rm -rf`, `mkfs`, `del /f /s /q` 等），工具会自动拦截。 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import time, urllib.request Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
proc = subprocess.Popen( The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 300 lines · 36 tokens per session scan C 1fee83b818c4
Bash Tool is a skill published in the GitHub repository valkryhx/google_adk_agent (6 stars, last pushed 4mo ago), with no licence file. It adds 36 tokens to every session and 3,033 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 3 findings (recursive force delete, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
create-task
Create and verify recurring or one-shot reminders, scripts, agent jobs, reports, and interactive skill launches.
task
Create, edit, and manage scheduled tasks. Tasks live at /.abtars/tasks/ — each task is a directory.
browser
Full browser capability — managed Browsie session or emergency Main direct mode.
linear
Manage Linear issues, projects, cycles, and documents via API.
model-scout
Find the best free cloud models and update models.json from OpenRouter leaderboard.
twitterX
Fetch Twitter/X content — single tweets (no auth) or feeds (cookies).