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/ykdojo/antigravity-cloud-run/half-clonenpx skills add ykdojo/antigravity-cloud-run --skill half-clonegit clone --depth 1 https://github.com/ykdojo/antigravity-cloud-runWrote 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/skills/ykdojo/antigravity-cloud-run/half-clone)<a href="https://agentmods.dev/skills/ykdojo/antigravity-cloud-run/half-clone"><img src="https://agentmods.dev/badge/skills/ykdojo/antigravity-cloud-run/half-clone.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 | $0.00049 | $0.00223 |
| Opus 5 | $0.00024 | $0.00112 |
| Sonnet 5 | $0.00010 | $0.00045 |
| Haiku 4.5 | $0.00005 | $0.00022 |
Grade B, and why
half-clone scanned grade B 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 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.
bash ~/.gemini/config/skills/half-clone/scripts/half-clone.sh What it actually says
Half-clone the conversation
Clones the later half of the most recent conversation (usually this one) into a new conversation, cutting at the middle user turn. The original is untouched; the clone starts with half the context.
Steps
- Run the bundled script:
bash ~/.gemini/config/skills/half-clone/scripts/half-clone.sh
-
It prints the new conversation id and how many steps were kept. Live conversations are safe to clone (the copy is a consistent snapshot).
-
Tell the user: open the clone with
/resume- it's the newest entry, titled after its first kept message. This current conversation stays as-is, so they should switch to the clone to benefit from the smaller context.
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 · 29 lines · 49 tokens per session scan B fdd6b78b39b7
half-clone is a skill published in the GitHub repository ykdojo/antigravity-cloud-run (2 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 223 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
bash
Bash shell scripting for automation, pipelines, and system administration. Use for .sh files and Linux scripting.
dx-optimizer
Expert developer experience optimizer specializing in build performance, tooling efficiency, and workflow automation. Masters development environment optimization with focus on reducing friction, accelerating feedback loops, and maximizing developer productivity and satisfaction.
slack-expert
Expert Slack platform specialist for Slack app development, @slack/bolt implementation, Block Kit UI, event handling, OAuth flows, and Slack API integrations. Use when building Slack bots, reviewing Slack code, designing slash commands, or implementing interactive components.
tooling-engineer
Expert tooling engineer specializing in developer tool creation, CLI development, and productivity enhancement. Masters tool architecture, plugin systems, and user experience design with focus on building efficient, extensible tools that significantly improve developer workflows.
m365-admin
Microsoft 365 administrator specializing in Exchange Online, Teams, SharePoint, licensing, Graph API automation, and secure identity operations.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.