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 MarcosNahuel/antigravity-plugin-cc --skill agy-promptinggit 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/skills/marcosnahuel/antigravity-plugin-cc/agy-prompting)<a href="https://agentmods.dev/skills/marcosnahuel/antigravity-plugin-cc/agy-prompting"><img src="https://agentmods.dev/badge/skills/marcosnahuel/antigravity-plugin-cc/agy-prompting/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/marcosnahuel/antigravity-plugin-cc/agy-prompting"><img src="https://agentmods.dev/badge/skills/marcosnahuel/antigravity-plugin-cc/agy-prompting.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 | $0.00040 | $0.00820 |
| Opus 5 | $0.00020 | $0.00410 |
| Sonnet 5 | $0.00008 | $0.00164 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade B, and why
agy-prompting 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 11d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
- Following structured-output instructions (markdown tables, JSON, frontmatter). How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompting agy (Gemini 3.x via Antigravity CLI)
Use this skill ONLY inside the antigravity:agy-rescue subagent when shaping the text you pass to agy --print. Do not use it to do independent reasoning, file inspection, or research yourself.
What agy is good at
- Native web search with citation grounding (real URLs, not hallucinated).
- Long-context reasoning over multiple sources.
- Following structured-output instructions (markdown tables, JSON, frontmatter).
- Tool calling for code generation and file edits when run with
--dangerously-skip-permissions.
What agy is worse at than Claude
- Following complex multi-turn workflow rules. Keep the prompt single-shot and self-contained.
- Inferring implicit context — if a constraint matters, write it down.
- Localized linguistic nuance — explicitly ask for the target dialect ("Spanish (Argentina)", "Brazilian Portuguese", etc.) when the output language matters.
Prompt shape that works
<TASK in one sentence>.
Rules:
- <constraint 1>
- <constraint 2>
- ...
Output format:
<exact markdown / json schema you want>
<DATA / TOPIC>:
<the actual content>
Keep the rules to <= 8 bullets. More than that and Gemini starts dropping the tail.
Things to ALWAYS include
- Output language when relevant.
- Whether citations are required and the citation format ([N] style works best).
- The exact output structure with markdown headers.
- An anti-hallucination clause ("if you could not find a solid source, say so explicitly" / "mark weak claims as [WEAK EVIDENCE]").
Things to AVOID
- Multi-step "first do X, then do Y, then call me back" instructions. agy in
--printmode is single-shot; chain steps from the caller side instead. - Demanding more than ~20 sources unless the user asked for it — quality drops fast past that.
- Free-form "be creative" — for research, structure is what makes the output usable.
- Mixing rescue work (code edits) and research (web search) in the same call. Pick one.
Routing flags reminder
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.
- 11d ago First seen · 72 lines · 40 tokens per session scan B 0581f4844cb7
agy-prompting is a skill published in the GitHub repository MarcosNahuel/antigravity-plugin-cc (28 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 820 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gemini-prompting
Internal guidance for composing effective grounded search queries.
gpt-image-2-prompting
Prompt OpenAI's GPT Image 2 — the five-slot Scene/Subject/Details/Use case/Constraints template it responds to, the change-versus-preserve shape for edits, labelled multi-image compositing, and how to get text on an image to render verbatim. Use whenever the model id contains gpt-image-2 (openai/gpt-image-2…
qwen-image-prompting
Prompt Alibaba's Qwen-Image line for the typography work it is built for — quoting exact copy so the model stops inventing it, switching prompt expansion off before it rewrites your strings, describing layout in relative position and weight rather than point sizes, writing non-Latin scripts as characters, and…
stable-audio-prompting
Prompt Stability's Stable Audio line — the genre/instruments/mood/BPM order its training metadata expects, the TrackType and VocalType tags that separate music, stems and sound effects on Stable Audio 3, matching duration to what you described, which checkpoints guidancescale and step count actually affect, and…
flux-2-klein-prompting
Prompt Black Forest Labs' FLUX.2 [klein] — the subject/environment/style/technical hierarchy it processes in order, guidance-scale and step choices, negative prompts aimed at real failure modes, and the seed-locked one-variable-at-a-time loop its sub-second latency makes practical. Use whenever the model id contains…
hailuo-prompting
Prompt MiniMax's Hailuo video line — the chronological beat order it animates from, the fifteen bracketed camera commands the Director endpoints accept and the three-per-bracket rule, when to switch promptoptimizer off, why there is no negative prompt to fall back on, and prompting the delta on image-to-video. Use…