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/jidohyun/claude-ssWrote 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/jidohyun/claude-ss/ss)<a href="https://agentmods.dev/commands/jidohyun/claude-ss/ss"><img src="https://agentmods.dev/badge/commands/jidohyun/claude-ss/ss.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 | $0.00012 | $0.00164 |
| Opus 5 | $0.00006 | $0.00082 |
| Sonnet 5 | $0.00002 | $0.00033 |
| Haiku 4.5 | $0.00001 | $0.00016 |
Grade A, and why
ss 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 7d 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.
What it actually says
/ss — attach latest screenshot
Run claude-ss queue to list pending screenshots. Take the most recent one (last line of output), then:
- Use the Read tool on that file path so the image is loaded visually into this conversation.
- After reading, run
rm "<that path>"to remove it from the queue. - In your next reply, confirm which screenshot was loaded (by filename) and then answer the user's question using the image.
If the queue is empty, tell the user the queue is empty and remind them to press the claude-ss hotkey (cmd+shift+2 by default) to capture one.
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.
- 7d ago First seen · 15 lines · 12 tokens per session scan A 5189539c0b21
ss is a command published in the GitHub repository jidohyun/claude-ss (3 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 164 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
config
Configure iterm2-tab-status plugin settings (emoji prefixes, colors, display target, subtitle activity, badge, notifications).
toggle-speak
Toggle whether Claude speaks each response aloud automatically via the Stop hook.
uninstall
Remove iTerm2 tab status adapter, venv (if created by iterm2-tab-status), and signal files.
calibrate
Record where the tab title sits on this machine (run once before the first rename).
rename
Rename the active Claude Code session tab in VS Code.
watch
Open a YouTube URL in your browser so the watcher plugin can auto play/pause it.