maestro-fix-cycle

maestro-fix-cycle is a skill for Claude Code from parisgroup-ai/imersao-ia-setup. It costs 73 tokens per session (3,825 once invoked), scanned A, original, MIT.

An automatic repair cycle for Maestro mobile test flows running on the iOS Simulator. Maestro is a tool that describes mobile actions in YAML files; the cycle handles one flow at a time and remembers its progress.

In plain words
What is it for?
Use it to fix authentication, student, or other Maestro flows, resume an interrupted repair cycle, inspect progress, reset its memory, or debug a flow in Maestro Studio.
Why use it?
It reduces the repeated work of investigating a failed mobile test, changing the flow or app code, and running the test again. Saved history and failure details help continue the work later.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the imersao plugin — 51 skills, 7 commands shipped together

Good fit Use it to fix authentication, student, or other Maestro flows, resume an interrupted repair cycle, inspect progress, reset its memory, or debug a flow in Maestro Studio.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/parisgroup-ai/imersao-ia-setup/maestro-fix-cycle
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add parisgroup-ai/imersao-ia-setup --skill maestro-fix-cycle
Clone the repo
git clone --depth 1 https://github.com/parisgroup-ai/imersao-ia-setup

Made for: Claude Code.

Or install imersao, the plugin that ships this one along with the rest of its 51 skills, 7 commands.

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 maestro-fix-cycle

README.md
[![agentmods](https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/maestro-fix-cycle/github.svg)](https://agentmods.dev/skills/parisgroup-ai/imersao-ia-setup/maestro-fix-cycle)
Your own site
<a href="https://agentmods.dev/skills/parisgroup-ai/imersao-ia-setup/maestro-fix-cycle"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/maestro-fix-cycle/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 maestro-fix-cycle

Your own site · 80×15
<a href="https://agentmods.dev/skills/parisgroup-ai/imersao-ia-setup/maestro-fix-cycle"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/maestro-fix-cycle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,825 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 $0.00073 $0.03825
Opus 5 $0.00036 $0.01912
Sonnet 5 $0.00015 $0.00765
Haiku 4.5 $0.00007 $0.00382

Measured 11d ago against content hash 58c804f7a5b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

maestro-fix-cycle 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 11d 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/imersao/skills/maestro-fix-cycle/SKILL.md · 466 lines

How it starts

The opening of the file, as written. The whole thing — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.

maestro-fix-cycle - Flow-by-Flow Test-Fix Loop with Memory

Processes Maestro flows one at a time, maintaining state across sessions. Analyzes failures, fixes YAML flows or app code, and re-runs until all pass.

Usage

/maestro-fix-cycle                    # Start/continue cycle
/maestro-fix-cycle auth               # Only auth flows
/maestro-fix-cycle student            # Only student flows
/maestro-fix-cycle continue           # Resume from last position
/maestro-fix-cycle reset              # Clear memory and start fresh
/maestro-fix-cycle status             # Show current progress
/maestro-fix-cycle studio             # Debug current flow in Maestro Studio

Memory System

State persisted in apps/mobile/.maestro-cycle/:

.maestro-cycle/
├── state.json           # Current position, queued flows
├── history.jsonl        # All fixes applied (append-only)
├── learnings.md         # Patterns discovered (human-readable)
└── failures/            # Detailed failure logs per flow
    └── {flow-name}.json

state.json

{
  "version": "1.0",
  "started_at": "2026-03-01T18:00:00Z",
  "updated_at": "2026-03-01T18:45:00Z",
  "current_flow": "flows/auth/login.yaml",
  "current_iteration": 1,
  "queue": [
    "flows/auth/token-refresh.yaml",
    "flows/student/courses-pagination.yaml"
  ],
  "completed": [
    "flows/smoke/smoke.yaml"
  ],
  "failed_permanently": [],
  "total_fixes": 3,
  "session_id": "abc123"
}

learnings.md

# Maestro Fix Learnings

> Auto-updated by maestro-fix-cycle. Manual edits welcome.

## Known Patterns

### Pattern: text-mismatch
- **Symptoms:** tapOn/assertVisible fails — element not found by text
- **Cause:** Button/label text in app differs from flow YAML
- **Solution:** Update text in YAML, or migrate to testID
- **How to find correct text:** Check component source or use `maestro studio`

### Pattern: locale-mismatch
- **Symptoms:** English text assertion fails on pt-BR simulator
- **Cause:** Simulator locale differs from flow expectations
- **Solution:** Use testID selectors (locale-independent)
- **Files seen:** All flows using text-based selectors

### Pattern: animation-timing
- **Symptoms:** Step fails intermittently after navigation
- **Cause:** waitForAnimationToEnd resolves before render completes
- **Solution:** Add explicit assertVisible for target element after wait

Read the full file on GitHub · 466 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. 11d ago First seen · 466 lines · 73 tokens per session scan A 58c804f7a5b0

Subscribe to this mod's changes

maestro-fix-cycle is a skill published in the GitHub repository parisgroup-ai/imersao-ia-setup (1 stars, last pushed 29d ago), licensed MIT. It adds 73 tokens to every session and 3,825 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

test-native-extension

Validate a third-party control repo across four automated layers plus one printed manual recipe. Layer 1 asserts native-source structure (Android getName() and iOS +moduleName to manifest nativeModule; @ReactMethod / RCTEXPORTMETHOD to methods; no @ReactModule) plus load/init readiness (ReactPackage public no-arg…

microsoft/power-platform-skills · 211 tokens

asc-shots-pipeline

Orchestrate iOS screenshot automation with xcodebuild/simctl for build-run, AXe for UI actions, JSON settings and plan files, Koubou-based framing (asc screenshots frame), and screenshot upload (asc screenshots upload). Use when users ask for automated screenshot capture, AXe-driven simulator flows, frame composition…

rorkai/app-store-connect-cli-skills · 79 tokens

mobile-testing-detox

Detox E2E gray-box testing for React Native - matchers, actions, expectations, waitFor, device API, synchronization, mocking, artifacts, CI integration.

agents-inc/skills · 38 tokens

mobile-testing-maestro

Maestro mobile E2E testing - YAML flows, selectors, flow control, environment variables, JavaScript expressions, device interactions, Maestro Studio, Maestro Cloud CI, tags, test suites.

agents-inc/skills · 42 tokens

ios-device-qa

Use when the user runs /ios-device-qa to drive a real iPhone over USB through a debug-bridge daemon and return a device QA report with verified interactions. Do not use for remote, credential, publish, deploy, or irreversible changes.

OutlineDriven/odin-claude-plugin · 55 tokens

xcode-simulator-testing

Use when asked to run /xcode-simulator-testing with a scheme name or current to build and launch an iOS app in a simulator. Not for project regeneration: use ios-build-fix.

OutlineDriven/odin-claude-plugin · 46 tokens