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 ShockRock2004/kamar-taj --skill askagygit clone --depth 1 https://github.com/ShockRock2004/kamar-tajWrote 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/shockrock2004/kamar-taj/askagy)<a href="https://agentmods.dev/skills/shockrock2004/kamar-taj/askagy"><img src="https://agentmods.dev/badge/skills/shockrock2004/kamar-taj/askagy/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/shockrock2004/kamar-taj/askagy"><img src="https://agentmods.dev/badge/skills/shockrock2004/kamar-taj/askagy.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 | $0.00085 | $0.01275 |
| Opus 5.5 | $0.00034 | $0.00510 |
| Sonnet 5.5 | $0.00017 | $0.00255 |
| Haiku 4.5 | $0.00009 | $0.00128 |
Grade A, and why
askagy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ask Agy
Overview
agy is the Antigravity CLI — a separate agent process on this machine, reachable non-interactively. It is a cold-start agent: it cannot see this conversation, the files you have open, or anything you already know. Its answer is only as good as the context you hand it in a single string.
Core principle: the prompt is the entire interface. Build it deliberately, then relay the reply as agy's, not your own.
Step 0 — Find agy, or stop
Resolve the binary before doing anything else. First hit wins:
AGY="$(command -v agy 2>/dev/null)"
[ -z "$AGY" ] && [ -x "$HOME/AppData/Local/agy/bin/agy.exe" ] && AGY="$HOME/AppData/Local/agy/bin/agy.exe"
[ -z "$AGY" ] && [ -x "$HOME/.local/bin/agy" ] && AGY="$HOME/.local/bin/agy"
[ -z "$AGY" ] && [ -x "/usr/local/bin/agy" ] && AGY="/usr/local/bin/agy"
echo "${AGY:-NOT_FOUND}"
If it resolves, carry $AGY through every call below. If it prints NOT_FOUND:
Say so plainly and stop. Tell the user the Antigravity CLI is not installed or not on
PATH, and that/askagyneeds it. Offer to answer the question yourself instead, clearly labelled as your own view rather than a second opinion.
Never fabricate a second opinion. A made-up "agy says…" is worse than no second opinion at all — the entire value of this skill is that the answer came from a different process.
The Prompt Recipe
Write the prompt as these four parts, in this order:
- Task framing — one sentence naming the role and the job. "You are reviewing a Python data pipeline for correctness bugs."
- Context agy cannot see — the relevant code, error text, file paths, versions, constraints, and what has already been tried and ruled out.
- The specific question — one question, sharply stated. Not three loosely related ones.
- Output shape — how you want the answer back. "List each bug as: file:line, one-sentence cause, minimal fix." Or "Answer in under 200 words, no preamble."
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 87 lines · 85 tokens per session scan A 313337b3e90f
askagy is a skill published in the GitHub repository ShockRock2004/kamar-taj (5 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 1,275 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 2026-08-31.
Other skills, from other repositories
social-post
A workflow for planning, writing, publishing, and evaluating social-media posts in the user's established voice. It covers Facebook, Instagram, YouTube, Threads, and X, including selected comment operations.
socialpost
A set of instructions for planning, writing, and revising posts for Facebook, Instagram, Threads, YouTube, and X. It also covers matching an author's style and reviewing post performance evidence.
avoid-ai-design
Audit and rewrite frontend UI to remove generic AI design patterns ("AI slop"), both the first-order defaults (purple gradients, Inter, a centered hero over three cards, untouched shadcn) and the second-order "tasteful AI" ones (cream with terracotta, near-black with acid green, all-caps mono chrome, one accented…
comfyui
Drive a local ComfyUI install for image, video, and audio generation via its HTTP API. Use WHENEVER generating, rendering, or editing images/video/audio/hero assets with ComfyUI, Z-Image, Ideogram, FLUX, LTX, Wan, or when building, parameterizing, or running ComfyUI workflows. Covers the API client, workflow JSON…
anydesign
Extract the design of a screenshot, website URL or Figma file into a design.md with tokens, components, layout and brand rules, or copy one element (navbar, card, illustration) into an element.md with a rebuild or image-generation prompt. Use when the user wants to document, replicate, audit or reverse-engineer a…
minimax-h3
Use when writing or debugging prompts for MiniMax H3 (Hailuo 3) video-with-audio generation, running the open weights locally in ComfyUI, choosing a quant or an acceleration LoRA for the VRAM you have, wiring reference-to-video with images, video or audio, or when a generated clip produces gibberish speech, drifts off…