agy-implement SKILL.md skillA

agy-implement from aarontzeng/dev-lead is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add aarontzeng/dev-lead/agy-implement@git:20260925.1e36cce

Pins git:20260925.1e36cce in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
aarontzeng/dev-lead
Path
skills/agy-implement/SKILL.md
Versions recorded
5
Latest version
git:20260925.1e36cce, committed Sep 25, 2026
First version recorded
Sep 11, 2026
Size
14,415 bytes
Repository stars
3
License
MIT

Delegate an implementation task to a headless Antigravity (`agy`) session in write mode, inside an isolated git worktree, then verify the result with a cross-family review pass before it merges. Use when the user wants a second model family's implementation attempt, wants to offload a well-scoped coding task, or explicitly asks to let agy implement something.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Delegate implementation to agy, then verify

Complements `agy-adversarial-review` (review-only intent via `--mode plan`).
This skill goes the other direction: agy **writes code**, so the safety comes
from three stacked boundaries — worktree isolation, the sandbox with a
targeted allow-list, and mandatory review before anything reaches the main
branch.

## Before the first run of a session

Read **[`../agy-adversarial-review/references/agy-runtime.md`](../agy-adversarial-review/references/agy-runtime.md)**.
It holds the
family-level mechanics shared by both agy roles — the permission allow-list,
the `--add-dir` workspace trap, the silent-death mode, auth diagnosis, and
the model catalogue. This file assumes you know them and covers only what
makes a run an *implementation*.

Three runtime facts this role depends on directly:

- **This role needs TOOL permissions, not just the `unsandboxed(...)` shell
  rules — and it is the role that finds out.** An empty `permissions.allow`
  loads as `permissions=<nil>` and falls back to asking a human who is not
  there, so the first tool call is auto-denied and the run dies having read
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add aarontzeng/dev-lead/agy-implement@sha256:78ccd40d0c2a79bb

The line at the top of this page pins the label git:20260925.1e36cce, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_bnjgizfqgw6fedyg.svg)](https://markdownregistry.com/a/art_bnjgizfqgw6fedyg)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Sep 11, 2026 and Sep 25, 2026, about one every 3 days.

versioncommittedcommitsizeaudit
git:20260925.1e36cce latest2026-09-25 1e36cce 14,415 BA view · diff
git:20260924.94205d42026-09-24 94205d4 14,405 BA view · diff
git:20260923.24cf1ad2026-09-23 24cf1ad 14,438 BA view · diff
git:20260922.cdb9a042026-09-22 cdb9a04 14,403 BA view · diff
git:20260911.4701f7c2026-09-11 4701f7c 14,278 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (14415 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

aarontzeng/dev-lead · 3 stars · license MIT · pushed 2026-10-19 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_bnjgizfqgw6fedyg
GET https://markdownregistry.com/api/v1/resolve?ref=aarontzeng/dev-lead/agy-implement
GET https://markdownregistry.com/api/v1/blob/78ccd40d0c2a79bb080b36178e9c1f553d35eb682d3df86e706140210668e97a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from aarontzeng/dev-lead

agy-adversarial-review SKILL.md skill
aarontzeng/dev-lead · skills/agy-adversarial-review/SKILL.md · Run an adversarial (red-team) review through the Antigravity CLI (`agy`, Gemini family). Use when the user asks for an…
git:20261018.d5ba9d5 · audit A · 3 stars
claude-adversarial-review SKILL.md skill
aarontzeng/dev-lead · skills/claude-adversarial-review/SKILL.md · Run an adversarial (red-team) review through headless Claude Code (`claude -p`, plan mode) as the review leg. Use when…
git:20260924.70f6701 · audit A · 3 stars
claude-implement SKILL.md skill
aarontzeng/dev-lead · skills/claude-implement/SKILL.md · Delegate a well-scoped implementation to headless Claude Code (`claude -p`, acceptEdits) in an isolated git worktree…
git:20261001.d64f4de · audit A · 3 stars
codex-adversarial-review SKILL.md skill
aarontzeng/dev-lead · skills/codex-adversarial-review/SKILL.md · Run a read-only Codex challenge review of a git diff with `codex exec` and the suite's adversarial framing (the Codex…
git:20260930.9533005 · audit A · 3 stars
codex-implement SKILL.md skill
aarontzeng/dev-lead · skills/codex-implement/SKILL.md · Delegate a well-scoped implementation to OpenAI Codex through its Claude Code companion plugin in an isolated git…
git:20260925.1a5468f · audit A · 3 stars
config SKILL.md skill
aarontzeng/dev-lead · skills/config/SKILL.md · View and change the dev-lead leg roster — which model and effort each adapter runs, per role and per round. Use when…
git:20261010.bb1f9c4 · audit A · 3 stars
cursor-adversarial-review SKILL.md skill
aarontzeng/dev-lead · skills/cursor-adversarial-review/SKILL.md · Run a read-only challenge review through Cursor's CLI (cursor-agent) in ask mode. Use when the user asks for a review…
git:20261007.90c283f · audit A · 3 stars
cursor-implement SKILL.md skill
aarontzeng/dev-lead · skills/cursor-implement/SKILL.md · Dispatch an implementation task to Cursor's CLI (cursor-agent) in an isolated worktree, with the model pinned to…
git:20260922.418bfd5 · audit A · 3 stars
dev-lead SKILL.md skill
aarontzeng/dev-lead · skills/dev-lead/SKILL.md · Orchestrate a feature or PR end-to-end as the lead — dispatch implementation to a delegate family based on task risk…
git:20261018.d5ba9d5 · audit A · 3 stars
grok-adversarial-review SKILL.md skill
aarontzeng/dev-lead · skills/grok-adversarial-review/SKILL.md · Run a read-only challenge review through xAI's Grok Build CLI (Grok family). Use when the user asks for an adversarial…
git:20260925.e471e34 · audit A · 3 stars
grok-implement SKILL.md skill
aarontzeng/dev-lead · skills/grok-implement/SKILL.md · Dispatch an implementation task to xAI's Grok Build CLI (Grok family) in an isolated worktree. Use when the user asks…
git:20260925.e471e34 · audit A · 3 stars
opencode-adversarial-review SKILL.md skill
aarontzeng/dev-lead · skills/opencode-adversarial-review/SKILL.md · Run an adversarial (red-team) review through the OpenCode CLI's free model pool (muse-spark, Nemotron, stealth models)…
git:20261004.3ab2900 · audit A · 3 stars

Every file in aarontzeng/dev-lead

Browse by kind, by grade A, or by owner.