agy-diff-inspector

agy-diff-inspector is a skill for Claude Code from iicmaster/antigravity-plugins. It costs 45 tokens per session (837 once invoked), scanned A, original, MIT.

A multi-stage inspector for reviewing Git changes, such as edits in a working tree, staged changes, or branch differences. It examines intent, program behavior, attack cases, possible regressions, and follow-up checks.

In plain words
What is it for?
Use it to adversarially audit code before merging, trace how changed state moves through the system, assess the affected areas, and produce a structured verification plan.
Why use it?
It helps uncover bugs, race conditions, security problems, and wider effects that a quick line-by-line review may miss.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node plugins/agy/skills/agy/scripts/agy-codex.mjs review "Apply sqthink diff inspection: focus on concurrency and regressions".

Part of the agy plugin — 5 skills, 7 commands, 1 agent, 1 MCP server shipped together

Good fit Use it to adversarially audit code before merging, trace how changed state moves through the system, assess the affected areas, and produce a structured verification plan.

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/iicmaster/antigravity-plugins
agentmods
npx agentmods add skills/iicmaster/antigravity-plugins/agy-diff-inspector

Made for: Claude Code.

Or install agy, the plugin that ships this one along with the rest of its 5 skills, 7 commands, 1 agent, 1 MCP server.

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-diff-inspector

README.md
[![agentmods](https://agentmods.dev/badge/skills/iicmaster/antigravity-plugins/agy-diff-inspector.svg)](https://agentmods.dev/skills/iicmaster/antigravity-plugins/agy-diff-inspector)
Your own site
<a href="https://agentmods.dev/skills/iicmaster/antigravity-plugins/agy-diff-inspector"><img src="https://agentmods.dev/badge/skills/iicmaster/antigravity-plugins/agy-diff-inspector.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 837 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 $0.00045 $0.00837
Opus 5 $0.00023 $0.00418
Sonnet 5 $0.00009 $0.00167
Haiku 4.5 $0.00005 $0.00084

Measured 7d ago against content hash 57165d22bc61, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agy-diff-inspector 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 7d 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.

plugins/agy/skills/agy-diff-inspector/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGY Diff Inspector (agy-diff-inspector)

Use this skill when you need an autonomous, deep adversarial inspection of code changes (Git Working Tree, Staged Changes, or Branch Diffs) via Google Antigravity (agy) guided by Sequential Thinking (sqthink).

Unlike surface-level code reviews, agy-diff-inspector breaks down diff hunks through a systematic, multi-stage reasoning pipeline to catch elusive bugs, race conditions, and security flaws before merge.


🧠 The Sequential Thinking (sqthink) Diff Audit Pipeline

Every inspection follows a strict 5-stage sequential reasoning pipeline:

flowchart TD
    S1["Stage 1: Intent & Invariant Mapping"] --> S2["Stage 2: Semantic & State Flow Tracing"]
    S2 --> S3["Stage 3: Adversarial Stress-Testing (Black-Hat)"]
    S3 --> S4["Stage 4: Blast Radius & Regression Analysis"]
    S4 --> S5["Stage 5: Structured Triage & Verification Plan"]

Stage 1: Intent & Invariant Mapping (ทำความเข้าใจเป้าหมายและแกนระบบ)

  • Parse commit intent or PR goal.
  • Map the invariant constraints of modified modules (e.g. read-only guarantees, transaction boundaries, idempotency).

Stage 2: Semantic & State Flow Tracing (ไล่เส้นทาง State และ Data Flow)

  • Trace modified variables, function signatures, and async lifecycles across callers.
  • Identify implicit type coercions, unhandled null/undefined branches, and un-awaited promises.

Stage 3: Adversarial Stress-Testing / Black-Hat Mode (สวมหมวกดำเค้นหาจุดพัง)

  • 💥 Concurrency & Race Conditions: What happens when two requests hit this code concurrently? Is shared state locked/isolated?
  • 🔒 Security Boundary Violations: Are inputs sanitized? Can parameters be manipulated? Are secrets or tokens leaked in logs?
  • ⏱️ Timeouts & Resource Exhaustion: Are loops bounded? Are sockets and file handles properly released in finally blocks?

Stage 4: Blast Radius & Regression Analysis (ประเมินผลกระทบวงกว้าง)

  • Check downstream dependencies for broken contracts.
  • Evaluate backwards compatibility of altered schemas, APIs, or database queries.

Read the full file on GitHub · 74 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. 7d ago First seen · 74 lines · 45 tokens per session scan A 57165d22bc61

Subscribe to this mod's changes

agy-diff-inspector is a skill published in the GitHub repository iicmaster/antigravity-plugins (6 stars, last pushed 15d ago), licensed MIT. It adds 45 tokens to every session and 837 once invoked, about $0.0002 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.