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 commands/marcosnahuel/antigravity-plugin-cc/reportgit 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/report)<a href="https://agentmods.dev/commands/marcosnahuel/antigravity-plugin-cc/report"><img src="https://agentmods.dev/badge/commands/marcosnahuel/antigravity-plugin-cc/report.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 | $0.00038 | $0.02229 |
| Opus 5 | $0.00019 | $0.01115 |
| Sonnet 5 | $0.00008 | $0.00446 |
| Haiku 4.5 | $0.00004 | $0.00223 |
Grade A, and why
report 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 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.
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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Two-phase orchestrator using the canonical TRAID Design System catalog of 5 templates: traid-dark, traid-light, stripe-press, notion-docs, magazine. Full specs in knowledge/traid/design-system/design-system.md.
Raw user request: $ARGUMENTS
Phase 1 — Parse and validate
- Parse optional flags:
--template <id>— if provided with a valid id (traid-dark | traid-light | stripe-press | notion-docs | magazine), SKIP Phase 2 and Phase 3 (analyze + ask) and use that template directly.--output <path>— custom output HTML path.--images <mode>—native(default) |external|none. Controls how![generate: ...]cues become images:native: agy generates each image itself (no external deps; quality/format inconsistent in headless agy — broken/missing images are caught by the Phase 5 check).external: agy only references<basename>.assets/<slug>.png; YOU (or the caller) pre-generate those PNGs with a dedicated image model. Recommended for brand-quality infographics. See "Image strategy" below.none: styled placeholders instead of images (no broken<img>).
- What remains after stripping flags is the markdown source path.
- If the source path is empty, ask once: "Which markdown file should agy turn into a report?"
- Resolve the source path against the current working directory if relative. If it doesn't exist or isn't readable, stop without invoking the subagent.
- Compute default output if
--outputomitted:output-slug= source filename minus extension, lowercased, non-alphanumeric →-, collapsed, trimmed 60 chars. (Distinct from the per-image<slug>used for![generate:]cues below.)date= today YYYY-MM-DD.output=docs/agy/reports/<date>-<output-slug>.htmlrelative to CWD.
- Ensure output dir exists:
mkdir -p docs/agy/reports
Phase 2 — Analyze (SKIP if --template was provided)
Invoke the antigravity:agy-rescue subagent with this header:
MODE: report-analyze
INTENSITY:
MODEL:
RESUME: false
WRITE_FILE:
SOURCE_FILE: <absolute path to source markdown>
USER_TEXT:
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 · 149 lines · 38 tokens per session scan A 8be1b2611bb7
report is a command published in the GitHub repository MarcosNahuel/antigravity-plugin-cc (26 stars, last pushed 20d ago), licensed MIT. It adds 38 tokens to every session and 2,229 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
gemini-swarm
Swarm a task across parallel Gemini (agy) sessions with automatic decomposition and model routing.
gemini-imagegen
Generate or edit an image via a Gemini (agy) session — Gemini's generateimage tool does what Claude cannot.
agy-debug
Send an error/stack trace plus the relevant file(s) to Antigravity (agy) for root-cause analysis.
agy-review
Send the current change set to Antigravity (agy) for a senior-reviewer code review.
agy-panel
Ask Antigravity (agy) the same question across several distinct models and compare their answers side by side.
agy
Consult Google's Antigravity CLI (agy) and relay its answer.