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 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/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/skills/ykdojo/antigravity-cloud-run/half-clone"><img src="https://agentmods.dev/badge/skills/ykdojo/antigravity-cloud-run/half-clone.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 | $0.00049 | $0.00223 |
| Opus 5.5 | $0.00020 | $0.00089 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 2mo ago), licensed MIT. It adds 49 tokens to every session and 223 once invoked, about $0.0002 per session on Opus 5.5. 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
zip
Create manualsetup.zip containing .agents/, preferences/, .claude/, .cursor/, and .grok/ folders, and the AGENTS.md, CLAUDE.md, webappagy.py, webappclaude.py, webappgrok.py, and webappgeminiapikey.py files for manual repository setup.
daily-read
Retrieve the scheduled daily bible readings for a given date or today, and retrieve the bible texts.
update
Download and extract the manual setup zip to initialize workspace directories.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
aident-loadout
Run multi-step work across apps the user connected in Aident Loadout: live action schemas, connection checks, cost preflight, and approval before side effects.
accint-commitments
Triage acc's open promises and close them with honest real-world verdicts via accact(runtime="outcome").