agentmods.dev

agy-cli

agy-cli is a skill for Claude Code, Codex from atharvakalele/Bridge. It costs 59 tokens per session (682 once invoked), scanned A, original, MIT.

A bridge for sending coding tasks from Grok to Antigravity CLI, a separate command-line coding worker, through MCP. It starts jobs in the background and reports their later status.

In plain words
What is it for?
Delegating coding work to Antigravity, starting or checking detached jobs, and continuing a worker conversation in the same project directory.
Why use it?
It lets a task continue outside the current chat instead of making the conversation wait for the worker to finish. It also keeps job queuing and status checking in one workflow.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for cline. Also seen: built for cline.

not rated 3repo 4d ago A scan 59 tokens original MIT

Good fit Delegating coding work to Antigravity, starting or checking detached jobs, and continuing a worker conversation in the same project directory.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/atharvakalele/bridge/agy-cli
View source ↗ atharvakalele/Bridge
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.

Any agent
npx skills add atharvakalele/Bridge --skill agy-cli
Clone the repo
git clone --depth 1 https://github.com/atharvakalele/Bridge

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for agy-cli

README.md
[![agentmods](https://agentmods.dev/badge/skills/atharvakalele/bridge/agy-cli/github.svg)](https://agentmods.dev/skills/atharvakalele/bridge/agy-cli)
Your own site
<a href="https://agentmods.dev/skills/atharvakalele/bridge/agy-cli"><img src="https://agentmods.dev/badge/skills/atharvakalele/bridge/agy-cli/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.

agentmods 80×15 button for agy-cli

Your own site · 80×15
<a href="https://agentmods.dev/skills/atharvakalele/bridge/agy-cli"><img src="https://agentmods.dev/badge/skills/atharvakalele/bridge/agy-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 682 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00059 $0.00682
Opus 5 $0.00030 $0.00341
Sonnet 5 $0.00012 $0.00136
Haiku 4.5 $0.00006 $0.00068

Measured 3d ago against content hash b55f5bd07d30, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agy-cli 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 3d 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.

skills/agy-cli/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delegate to Antigravity CLI

MCP server agy-cli is Grok user-scoped only. Tools: agy_run, agy_status, agy_models, agy_preview. Do not register this server on Cline or Claude.

AG is a detached worker. Do not run agy or agy-job inside this chat (that dies when the user types). Do not start waiter.sh.

Every job

  1. search_tool then agy_run with a full task and absolute cwd.
  2. Default model: gemini-3.7-flash-medium. Never Opus. Never Gemini Pro unless the user writes it.
  3. agy_run returns immediately (STARTED or QUEUED) with job_id.
  4. Start a background monitor; do not block the turn: python3 ~/.config/bridge/agy_cli/watch_job.py <job_id> One line: SUCCESS|ERROR|CRASH|TIMEOUT|NETWORK|CANCELED <id>
  5. Keep talking. When the monitor fires, agy_status and continue.

Same cwd continues the last AG conversation. Pass new_session=true only for a fresh AG chat.

Queue

If status is QUEUED, a job is already running. The new job starts when that one finishes. Do not spawn a second AG yourself.

Log pane

The AG-job window is logs only. Typing there does not talk to AG.

  • Closing it does not kill the job.
  • Logs stay until the user closes them. Do not close Grok's terminal (title is not AG-job).
  • If agy_status shows preview_open: false while the job is still running, ask: "You closed the AG log pane. Want it back?" Reopen only with agy_preview action=reopen after they say yes.

Other chats (same state)

Start Grok with grok-ide (loads GROK_SYSTEM_PROMPT.md). Restart Grok after ./scripts/install.sh.

This pipeline is Grok ↔ AG only. Only MCP server: agy-cli. Do not add it to Cline or Claude. Do not run agy-job or waiter.sh.

Playbook on disk: ~/.grok/skills/agy-cli/SKILL.md. Always-on Grok rule: ~/.grok/rules/agy-cli.md (every Grok chat, no extra briefing).

Finish kinds

  • SUCCESS — AG finished the task
  • ERROR — AG reported failure
  • CRASH — process died with no result
  • TIMEOUT — we cut it off at the time limit
  • NETWORK — connection / auth / 429 / 5xx
  • CANCELED — stopped before completion

Read the full file on GitHub · 52 lines

Files

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.

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. 3d ago First seen · 52 lines · 59 tokens per session scan A b55f5bd07d30

Subscribe to this mod's changes

agy-cli is a skill published in the GitHub repository atharvakalele/Bridge (3 stars, last pushed 4d ago), licensed MIT. It adds 59 tokens to every session and 682 once invoked, about $0.0003 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 2026-09-05.

Building agentsClaude Codeagentic-codingai-agentsantigravityclinecursor
Related

Other skills, from other repositories

chinese-git-workflow

A Git workflow guide tailored to Chinese-hosted platforms such as Gitee, Coding.net, and GitLab, including their code-review and build systems.

Leodorareluctant259/superpowers-zh · 33 tokens

chinese-commit-conventions

A Chinese-language convention for writing Git commit messages, based on Conventional Commits, a standard format that tools can use to classify changes and build changelogs.

Leodorareluctant259/superpowers-zh · 28 tokens

using-superpowers

A set of rules for finding and using assistant skills at the start of every conversation. It says to check for relevant skills before responding, including when asking a clarification question.

Leodorareluctant259/superpowers-zh · 38 tokens

chinese-code-review

Chinese-language guidance for giving professional, tactful code-review feedback while still calling out real problems.

Leodorareluctant259/superpowers-zh · 29 tokens

mcp-builder

A guide to building MCP servers, which let AI assistants call tools or read connected data. It covers server structure, tool design, validation, testing and deployment in TypeScript and Python.

Leodorareluctant259/superpowers-zh · 32 tokens

workflow-runner

A workflow runner that reads agency-orchestrator YAML files and carries out their steps inside Claude Code, OpenClaw, or Cursor. A YAML workflow is a text file describing inputs, roles, tasks, and their order.

Leodorareluctant259/superpowers-zh · 61 tokens