What is agy-task-rescue?

A troubleshooting skill for stuck tasks, complex regressions, failing tests, and difficult runtime bugs. It uses a separate Antigravity CLI process to investigate causes and verify fixes in a sandbox.

Investigating bugs, regressions, and failing test suites that need systematic diagnosis and a verified fix.

It provides a structured way to isolate a problem, test possible causes, create a small fix, and check that the fix does not break existing behavior.

agy-task-rescue — Skill for Claude Code by iicmaster

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-task-rescue

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/iicmaster/antigravity-plugins/agy-task-rescue/github.svg)](https://agentmods.dev/skills/iicmaster/antigravity-plugins/agy-task-rescue)

Your own site

<a href="https://agentmods.dev/skills/iicmaster/antigravity-plugins/agy-task-rescue"><img src="https://agentmods.dev/badge/skills/iicmaster/antigravity-plugins/agy-task-rescue/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/iicmaster/antigravity-plugins/agy-task-rescue"><img src="https://agentmods.dev/badge/skills/iicmaster/antigravity-plugins/agy-task-rescue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 744 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.

Model	Per session	Once invoked
Fable 5.1	$0.00046	$0.00744
Opus 5.5	$0.00018	$0.00298
Sonnet 5.5	$0.00009	$0.00149
Haiku 4.5	$0.00005	$0.00074

Measured 2mo ago against content hash 66c31f84c910, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agy-task-rescue 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 2mo 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-task-rescue/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGY Task Rescue (`agy-task-rescue`)

Use this skill when you encounter a stuck problem, complex regression, failing test suite, or tricky runtime bug that requires a systematic, sandboxed sub-agent investigation via Google Antigravity (agy) guided by Sequential Thinking (sqthink).

🧠 The Sequential Thinking (`sqthink`) Rescue Framework

Every rescue task follows a structured 5-step problem-solving discipline:

flowchart TD
    S1["1. Anomaly Isolation & Reproducer"] --> S2["2. Hypothesis Formulation (Root Cause)"]
    S2 --> S3["3. Diagnostic Falsification in Sandbox"]
    S3 --> S4["4. Minimal Safe Patch Synthesis"]
    S4 --> S5["5. Regression & Invariant Verification"]

1. Anomaly Isolation & Smallest Reproducer (แยกแยะอาการและจำลองปัญหา)

Extract the exact error message, stack trace, and failing preconditions.
Construct the minimal reproduction command/script to isolate the failure from noise.

2. Root Cause Hypothesis Formulation (ตั้งสมมติฐานต้นตอ)

Formulate 2-3 distinct hypotheses for why the failure occurs (e.g. race condition, unhandled edge-case input, incorrect environment assumption, stale cache).

3. Diagnostic Falsification in Sandbox (ทดสอบหักล้างสมมติฐาน)

Run isolated probes/tests in the sandboxed process to disprove incorrect hypotheses.
Narrow down to the single proven root cause with concrete evidence.

4. Minimal Safe Patch Synthesis (ออกแบบการแก้ไขที่เล็กที่สุดและปลอดภัย)

Draft the smallest contiguous edit that resolves the root cause.
Ensure no collateral damage or unneeded refactorings are introduced.

5. Regression & Invariant Verification (รันเทสต์ยืนยันผล 100%)

Execute relevant test commands (npm test, unit tests) to verify the patch turns Red into Green without causing new regressions.

🛡️ Sandbox Safety Guarantees

Strict Read-Only by Default: The rescue agent operates in read-only mode and proposes solutions unless file edits are explicitly requested.
Smallest Safe Diff: When file modification is requested, only the minimal necessary contiguous edit is applied.
Self-Contained Execution: Operates within workspace boundaries without leaking state to parent session.

Read the full file on GitHub · 75 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.

2mo ago First seen · 75 lines · 46 tokens per session scan A 66c31f84c910

Subscribe to this mod's changes

agy-task-rescue is a skill published in the GitHub repository iicmaster/antigravity-plugins (7 stars, last pushed 9d ago), licensed MIT. It adds 46 tokens to every session and 744 once invoked, about $0.0002 per session on Opus 5.5. 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.

Debugging

agy-task-rescue next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agy-task-rescueiicmaster/antigravity-plugins	Skill	7	9d ago	MIT	A	46	Claude Code
systematic-debuggingopen-metadata/OpenMetadata	Skill	16k	today	Apache-2.0	A	37	Claude Code
log-error-digestzebbern/claude-code-guide	Skill	4.7k	2d ago	MIT	A	71	Claude Code, Codex
incident-response-incident-responsermyndharis/antigravity-skills	Skill	2.0k	2d ago	MIT	A	36	Claude Code, Codex
cwv-optimizeradobe/skills	Skill	322	today	Apache-2.0	A	112	Claude Code
ci-fixersipyourdrink-ltd/bernstein	Skill	1.2k	yesterday	Apache-2.0	A	15	Claude Code, Codex
diagnosing-missing-recordingsPostHog/posthog	Skill	41k	today	none	A	76	Claude Code, Codex