agy-implementer

agy-implementer is a skill for Claude Code, Codex from keli-wen/agy-staff. It costs 83 tokens per session (1,101 once invoked), scanned A, a copy of implementer, MIT.

A launcher for handing a well-defined coding task to Google's Antigravity command-line agent. That agent edits the current working folder and can carry out explicitly requested Git delivery steps.

In plain words
What is it for?
Delegating implementation work to Antigravity, including tasks that modify files in a Git repository.
Why use it?
It lets another coding agent implement a scoped task while the launcher collects its result and passes along the requested delivery instructions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is Run this command **unsandboxed** — agy needs a localhost port and its OAuth token file, which harness sandboxes hide. In Codex, request escalated permissions fo.

Part of the agy plugin — 12 skills shipped together

Good fit Delegating implementation work to Antigravity, including tasks that modify files in a Git repository.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/keli-wen/agy-staff
agentmods
npx agentmods add skills/keli-wen/agy-staff/agy-implementer

Made for: Claude Code, Codex.

Or install agy, the plugin that ships this one along with the rest of its 12 skills.

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-implementer

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/keli-wen/agy-staff/agy-implementer"><img src="https://agentmods.dev/badge/skills/keli-wen/agy-staff/agy-implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,101 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 86% copy Near-identical to another mod 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 $0.00083 $0.01101
Opus 5 $0.00042 $0.00550
Sonnet 5 $0.00017 $0.00220
Haiku 4.5 $0.00008 $0.00110

Measured today against content hash c13c2f56fca7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agy-implementer 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 today.

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.

Origin

This is a copy

86% identical to implementer — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

pi-skills/agy-implementer/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agy implementer

Hand a coding task to the agy staffer. agy edits the real working tree under its unrestricted permission profile; the companion is a thin launcher and job collector. Pass the user's requested delivery through in the task text instead of doing Git work yourself.

Locating the companion

This skill file lives at <plugin-root>/pi-skills/agy-implementer/SKILL.md; resolve the companion path relative to this skill directory:

node "<skill-dir>/../../companion/agy-companion.mjs" implement [flags] --prompt "task description"

Pass the user's task description verbatim via --prompt; use --prompt-file <path> or --stdin for long text.

[!IMPORTANT] Run this command unsandboxed — agy needs a localhost port and its OAuth token file, which harness sandboxes hide. In Codex, request escalated permissions for the command. Details: ../agy-jobs/references/troubleshooting.md. (The companion passes --dangerously-skip-permissions to agy in this mode — that is the unrestricted profile working as designed.)

Workspace and delivery

  • Inside a git repository, dirty workspaces are allowed. When git status --porcelain is not clean, the companion injects a bounded pre-run status summary into the implement prompt so agy treats those paths as user-owned context.
  • Outside a git repository the companion warns that agy's edits cannot be reviewed or rolled back via git, and proceeds. Relay that warning; there is no diff to fall back on.
  • By default, agy leaves a working-tree diff. If the user explicitly asks for a commit, push, or PR, include that request verbatim in the task text and let agy do that exact Git delivery.
  • After the run, surface agy's summary and the current workspace state. Do not add your own commit/PR step unless the user separately asks you to do it.

Collecting the result

The command returns a job id. Read ../agy-jobs/SKILL.md and follow its collection and recovery flow; use one background wait <id> --timeout 10m per job. Deliver the result when ready; exit 2 means the worker is still running and the command has printed its current progress. To answer a progress question or give a mid-run update, call observe <id> as described in the jobs skill.

Read the full file on GitHub · 57 lines

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. today Changed · -2 lines c13c2f56fca7
  2. 3d ago First seen · 59 lines · 83 tokens per session scan A 27b15301a256

Subscribe to this mod's changes

agy-implementer is a skill published in the GitHub repository keli-wen/agy-staff (122 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 1,101 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to implementer, differing in 22 lines, and is treated as a copy.

Related

Other skills, from other repositories

conductor-revert

Reverts previous work (tracks, phases, or tasks) by identifying associated commits and performing Git reverts.

gemini-cli-extensions/conductor · 27 tokens

cc-commit-msg

A workflow for generating structured Git commit messages, which are short records describing changes made to a codebase.

doccker/cc-use-exp · 38 tokens

pr-review

Comprehensive code review for pull requests using parallel multi-agent analysis. Audits CLAUDE.md compliance, checks for bugs, analyzes git history, reviews comments, and filters by confidence score. Use when reviewing a GitHub PR, mentions "code review", "review this PR", or "/code-review".

saitarrun/Devforge-ai · 64 tokens

commit

Detect the repo's commit convention (Conventional Commits, Gitmoji, or a custom template) and create commits. Use when asked to commit, write a commit message, stage and commit changes, or commit and push work.

Bilal140202/the-lord-of-the-skills · 49 tokens

g-doc-review

Documentation review gate. Dispatches the doc-reviewer agent on the changed file set to check documentation currency against the code it describes, then issues a standalone DOCS READY or DOCS HOLD verdict. On DOCS READY it writes the doc-approval sentinel that the commit gate checks for doc/mixed commits. Read-only on…

onlygian/G-Forge · 102 tokens

g-retro

Synthesize a session retrospective from the silent-observer journal — no interview. Reads the passive activity log (.claude/journal/), git history, and g-docs/todo.md, and writes g-docs/retros/YYYY-MM-DD-topic.md with what happened, decisions inferred, patterns, and cold-start context.

onlygian/G-Forge · 69 tokens