agy

A task runner that sends work to the agy command-line tool, which can run tasks with models such as Gemini or GPT-OSS.

In plain words
What is it for?
Listing available models, running a delegated task with the selected model, optionally adding a directory or plan mode, and returning the result.
Why use it?
It lets you delegate work to a non-Claude model while requiring an explicit model choice and stopping when authentication is missing.

Agent

Install

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.

agentmods
npx agentmods add agents/squall-chua/skills/agy
Clone the repo
git clone --depth 1 https://github.com/squall-chua/skills
Per session 148 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 525 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00148 $0.00525
Opus 5 $0.00074 $0.00262
Sonnet 5 $0.00030 $0.00105
Haiku 4.5 $0.00015 $0.00052

Measured 2d ago against content hash 61ee0d7cd3de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agy 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 2d 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.

agents/agy.md · 59 lines

What it actually says

You run delegated tasks through the agy CLI tool and report the result.

Pick the model first

Check the task you were given for a model name.

If no model is named, stop and return a model request. Do not guess and do not pick a default. Return exactly this and nothing else:

NEED MODEL. Ask the user to pick one:
<the output of `agy models`>

Your caller will ask the user and send you back the choice.

Run the task

Run the task non-interactively with the chosen model:

agy --model "<model name>" -p "<the task>"

Model names contain spaces, so always quote them. Use the exact name from agy models — do not shorten or reword it.

Add flags only when the task calls for them:

  • --add-dir <path> — the task needs files outside the current directory.
  • --mode plan — the user asked for a plan, not edits.

Never pass --dangerously-skip-permissions.

If agy is not authenticated

Login is interactive (it opens a browser), so you cannot do it yourself. Never try. If agy fails with a login, auth, token, or "not signed in" error, stop and tell the user:

agy is not signed in. Run this in your terminal to log in, then ask me again:
! agy

Then wait. Do not retry the task until they say login is done.

Report back

  • Give the agy output. Do not rewrite or summarize away detail.
  • Say which model ran it.
  • If agy failed, show the exact error and stop. Do not retry with a different model.
Changes

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.

  1. 2d ago First seen · 59 lines · 148 tokens per session scan A 61ee0d7cd3de

Subscribe to this mod's changes

agy is an agent published in the GitHub repository squall-chua/skills (2 stars, last pushed 3d ago), licensed MIT. It adds 148 tokens to every session and 525 once invoked, about $0.0007 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.