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/MarcosNahuel/antigravity-plugin-ccWrote 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/marcosnahuel/antigravity-plugin-cc/media)<a href="https://agentmods.dev/commands/marcosnahuel/antigravity-plugin-cc/media"><img src="https://agentmods.dev/badge/commands/marcosnahuel/antigravity-plugin-cc/media/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/marcosnahuel/antigravity-plugin-cc/media"><img src="https://agentmods.dev/badge/commands/marcosnahuel/antigravity-plugin-cc/media.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 | $0.00080 | $0.00817 |
| Opus 5.5 | $0.00032 | $0.00327 |
| Sonnet 5.5 | $0.00016 | $0.00163 |
| Haiku 4.5 | $0.00008 | $0.00082 |
Grade A, and why
media 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 2mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multimodal Q&A over a media file. Give agy an audio/video/image (or a YouTube/remote URL) and a
question; it answers grounded in what it heard/saw, with time references for audio/video.
Raw user request: $ARGUMENTS
Phase 0 — Resolve source + question (ONE Bash call)
Parse $ARGUMENTS: split on the first | → left = source (a URL or an existing file), right =
question. If there is no |, the leading URL/existing-file token is the source and the rest is the
question. If the question is empty, ask once and stop.
python - "$SOURCE" "$PREGUNTA" <<'PYEOF'
import sys, os, re, hashlib
src = sys.argv[1].strip().strip('"'); preg = (sys.argv[2] if len(sys.argv) > 2 else "").strip()
AUD=(".ogg",".mp3",".wav",".m4a",".aac",".flac",".opus",".aiff"); VID=(".mp4",".mov",".webm",".mkv",".avi",".m4v")
IMG=(".png",".jpg",".jpeg",".webp",".gif")
low=src.lower()
if low.startswith("http"): kind="url"; addir=""
elif low.endswith(VID): kind="video"; addir=os.path.dirname(os.path.abspath(src))
elif low.endswith(AUD): kind="audio"; addir=os.path.dirname(os.path.abspath(src))
elif low.endswith(IMG): kind="image"; addir=os.path.dirname(os.path.abspath(src))
else: kind="file"; addir=os.path.dirname(os.path.abspath(src))
base=re.sub(r"[^a-z0-9]+","-", (re.sub(r"^https?://(www\.)?","",low) if kind=="url" else os.path.splitext(os.path.basename(src))[0]).lower()).strip("-")[:40] or "media"
qh=hashlib.sha1(preg.encode()).hexdigest()[:6]
out=os.path.join("docs","agy","media", f"{base}-{qh}.md"); os.makedirs(os.path.dirname(out), exist_ok=True)
print(f"KIND={kind}\nADD_DIR={addir}\nWRITE_FILE={os.path.abspath(out)}\nSOURCE={src}")
PYEOF
Phase 1 — Answer (ONE agy subagent)
Spawn ONE antigravity:agy-rescue subagent in MODE: media:
MODE: media
CWD: <absolute current working dir>
KIND: audio|video|image|url|file
SOURCE: <file path or URL>
ADD_DIR: <dir of the source file, or empty for a URL>
PREGUNTA: <question>
WRITE_FILE: <WRITE_FILE>
USER_TEXT:
(empty)
Phase 2 — Present
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.
- 2mo ago First seen · 64 lines · 80 tokens per session scan A b91270f693d2
media is a command published in the GitHub repository MarcosNahuel/antigravity-plugin-cc (32 stars, last pushed 26d ago), licensed MIT. It adds 80 tokens to every session and 817 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
media compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mediaMarcosNahuel/antigravity-plugin-cc | Command | 32 | 26d ago | MIT | A | 80 | Claude Code |
| gemini-imagegenVallykrie/gemini-swarm-skill | Command | 7 | 1mo ago | MIT | A | 22 | Claude Code |
| deepHayes-Zhang/deep-research | Command | 4 | 5mo ago | MIT | A | 27 | Claude Code |
| agy-debugAIgen-Solutions-s-r-l/agy-claude-plugin | Command | 1 | 5mo ago | MIT | A | 25 | Claude Code |
| agy-reviewAIgen-Solutions-s-r-l/agy-claude-plugin | Command | 1 | 5mo ago | MIT | A | 20 | Claude Code |
| agy-panelAIgen-Solutions-s-r-l/agy-claude-plugin | Command | 1 | 5mo ago | MIT | A | 22 | Claude Code |
| agyAIgen-Solutions-s-r-l/agy-claude-plugin | Command | 1 | 5mo ago | MIT | A | 14 | Claude Code |