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/record)<a href="https://agentmods.dev/commands/marcosnahuel/antigravity-plugin-cc/record"><img src="https://agentmods.dev/badge/commands/marcosnahuel/antigravity-plugin-cc/record/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/record"><img src="https://agentmods.dev/badge/commands/marcosnahuel/antigravity-plugin-cc/record.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 | $0.00038 | $0.01073 |
| Opus 5.5 | $0.00015 | $0.00429 |
| Sonnet 5.5 | $0.00008 | $0.00215 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
record 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 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.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Route this to the antigravity:agy-rescue subagent in MODE: record.
Raw user request: $ARGUMENTS
Routing rules
-
Parse the URL: the first whitespace-separated token of
$ARGUMENTSthat starts withhttp://orhttps://IS the URL. If the user wrote it without a scheme, prependhttps://. If no URL is found, ask once: "What URL should I record?". -
Steps: everything else in
$ARGUMENTS(whatever is not the URL) is the natural-language steps. If empty, use the default exploratory walkthrough (see template below). -
Slug: build from the URL's host + first path segment (e.g.
https://erp.traidagency.com/login→erp-traidagency-com-login). Lowercase, non-alphanumeric →-, collapse repeats, trim to 60 chars. -
Date: today in
YYYY-MM-DD(local time). -
Paths (all relative to current working directory):
OUTPUT_DIR=docs/agy/recordings/REPORT_FILE=docs/agy/recordings/<date>-<slug>.mdVIDEO_FILE=docs/agy/recordings/<date>-<slug>.webmMP4_FILE=docs/agy/recordings/<date>-<slug>.mp4(only if ffmpeg available)
-
Pre-flight: with ONE
Bashcall:mkdir -p docs/agy/recordings -
Hand off to subagent: pass this header block followed by the URL and steps:
MODE: record URL: <url> CWD: <absolute path to current working directory> OUTPUT_DIR: docs/agy/recordings REPORT_FILE: docs/agy/recordings/<date>-<slug>.md VIDEO_FILE: docs/agy/recordings/<date>-<slug>.webm STEPS: <natural-language steps, or "DEFAULT_WALKTHROUGH" if empty>
Default walkthrough (when no steps given)
If the user did not provide steps, instruct agy to:
- Navigate to the URL and wait for DOM ready.
- Take an initial screenshot.
- Scroll slowly to the bottom of the page in 3-4 steps.
- Scroll back to the top.
- Identify the most prominent visible CTA (button/link), click it. Do NOT type credentials or fill forms.
- Take a final screenshot.
- Stop.
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 · 77 lines · 38 tokens per session scan A f0a9e7294e57
record is a command published in the GitHub repository MarcosNahuel/antigravity-plugin-cc (30 stars, last pushed 8d ago), licensed MIT. It adds 38 tokens to every session and 1,073 once invoked, about $0.0002 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.
Other commands, from other repositories
e2e
Generate and run E2E tests with Playwright.
ia-test-browser
Run browser tests on pages affected by current PR or branch.
playwright-setup
Verify Playwright CLI installation and create a .playwright/cli.config.json configuration file. Use when setting up browser automation, configuring Playwright, or user mentions "setup playwright", "configure browser testing", "install playwright".
qa
Pre-PR quality gate — browser-driven QA for web changes with a mandatory evidence packet against a provisioned environment. No QA-passed claim without artifacts. Workspace-aware. For a quick behavioral check without the evidence packet, prefer the bundled /verify or /run.
create-smoke-test.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
qa
Dispatch a verifiable browser task to the qa-tester subagent. Use for regression checks, smoke tests, and any task with a clean pass/fail outcome. Supports an EXHAUSTIVE mode that verifies every control behind an honesty gate.