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 freestyler-arb/imagine-gemini-for-claude-codex --skill gemini-researchgit clone --depth 1 https://github.com/freestyler-arb/imagine-gemini-for-claude-codexWrote 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/freestyler-arb/imagine-gemini-for-claude-codex/gemini-research)<a href="https://agentmods.dev/skills/freestyler-arb/imagine-gemini-for-claude-codex/gemini-research"><img src="https://agentmods.dev/badge/skills/freestyler-arb/imagine-gemini-for-claude-codex/gemini-research/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/freestyler-arb/imagine-gemini-for-claude-codex/gemini-research"><img src="https://agentmods.dev/badge/skills/freestyler-arb/imagine-gemini-for-claude-codex/gemini-research.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 | $0.00112 | $0.01190 |
| Opus 5 | $0.00056 | $0.00595 |
| Sonnet 5 | $0.00022 | $0.00238 |
| Haiku 4.5 | $0.00011 | $0.00119 |
Grade A, and why
gemini-research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gemini-research
Overview
Use Google Gemini to research and synthesise over context you provide and return a structured, sourced answer. Good for large-context digestion (a big file, a whole module, many files at once), option comparisons, and "find/extract X across all of this" — all on the user's AI Pro subscription (agy), without spending the main agent's tokens or context window.
This is a specialised wrapper around gemini-pro with a research workflow and report format. It is not the branded Gemini web Deep Research agent (that does live web browsing in the Gemini app and is not exposed by agy -p). For freeform delegation use gemini-pro; for code/plan critique use gemini-review.
How to invoke
Pipe the corpus via stdin and ask for a structured, sourced answer. Pick the model by job size (see below).
# Digest a module into a structured brief — name the SPECIFIC files you need
cat src/orders/engine.py src/orders/state.py src/orders/api.py | gemini "$(cat <<'PROMPT'
Research question: how does the order lifecycle work end to end?
Produce: (1) a 5-bullet summary, (2) the key components and their roles,
(3) data flow start→finish, (4) risks/edge cases, (5) open questions.
Cite the file/function each claim comes from. Say "unknown" when the context
doesn't answer something — do not guess.
PROMPT
)"
# Compare options (no large context needed)
gemini "Compare Postgres LISTEN/NOTIFY vs Redis Streams vs a job queue for a 50 msg/s order pipeline. Give a recommendation with trade-offs and when each wins."
Don't pipe whole trees with globs like
cat src/**/*.py— enumerate the files you actually need. A blind glob sweeps inconfig/settings/.env-style files, test fixtures, and credentials and sends them to Google verbatim.
If gemini is not on PATH use ~/.local/bin/gemini or agy -p "<prompt>" --model "<model>".
Choosing the model
- Pro / High (default) — synthesis, comparisons, anything needing real reasoning.
-m flash— fast first-pass digestion of large/low-stakes context, or bulk extraction, to save the weekly quota.- Two-pass pattern for very large corpora:
flashto extract/summarise chunks → feed the summaries back into a Pro/High call to synthesise. Keeps cost down while keeping the final reasoning strong.
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 · 65 lines · 0 tokens per session scan A a2a654ff6d9f
gemini-research is a skill published in the GitHub repository freestyler-arb/imagine-gemini-for-claude-codex (4 stars, last pushed 2mo ago), licensed MIT. It adds 112 tokens to every session and 1,190 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
jobs
Manage agy staffer background jobs - collect results, check status, cancel, follow-up conversation, and setup. Use when an agy job needs collecting, when the user asks "is the agy job done", "show agy's result", "cancel the agy job", "continue the agy conversation", or "set up agy". This is the orchestrator's skill…
agy-lead
Orchestrate an ongoing task with AGY while the current agent owns key decisions, review, and delivery. Use when the user invokes /skill:agy-lead or asks you to coordinate a task using AGY.
implementer
Delegate a coding task to Google's Antigravity CLI (agy staffer, fast Gemini), which edits the working tree directly and can perform explicitly requested Git delivery. Use when the user says /agy:implementer, "have agy fix/build X", or wants to hand a well-scoped coding task to the agy staffer instead of doing it in…
researcher
Delegate a deep research or survey task to Google's Antigravity CLI (agy staffer, fast Gemini). Use when the user says /agy:researcher, "ask agy to research", "have the agy staffer survey X", or wants a second, independent deep-dive on a topic or codebase without spending the host model's quota.
staffer
Delegate a general-purpose task to Google's Antigravity CLI (agy staffer, fast Gemini) with a minimal, unopinionated prompt. Use when the user says /agy:staffer, "have agy do/handle X", "have agy generate an image", or the task fits none of the specialist personas (researcher / reviewer / implementer / ask) — the…
agy-ask
Ask Google's Antigravity CLI (agy staffer, fast Gemini) a cheap one-shot question - the fast zero-tool mode and the post-install smoke test. Use when the user says /skill:agy-ask, "ask agy", "quick second opinion from agy", or right after installing to verify the plugin works.