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.
git clone --depth 1 https://github.com/iicmaster/antigravity-pluginsnpx agentmods add skills/iicmaster/antigravity-plugins/agy-diff-inspectorWrote 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.
[](https://agentmods.dev/skills/iicmaster/antigravity-plugins/agy-diff-inspector)<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>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.
| Model | Per session | Once 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 |
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.
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/undefinedbranches, 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
finallyblocks?
Stage 4: Blast Radius & Regression Analysis (ประเมินผลกระทบวงกว้าง)
- Check downstream dependencies for broken contracts.
- Evaluate backwards compatibility of altered schemas, APIs, or database queries.
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.
- 7d ago First seen · 74 lines · 45 tokens per session scan A 57165d22bc61
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…