Borrowing it
Nothing to install: this file belongs to EastStarAI/sanad-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/EastStarAI/sanad-agent/main/.agents/skills/sanad-client-tester/SKILL.mdgit clone --depth 1 https://github.com/EastStarAI/sanad-agentWrote 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/eaststarai/sanad-agent/sanad-client-tester)<a href="https://agentmods.dev/skills/eaststarai/sanad-agent/sanad-client-tester"><img src="https://agentmods.dev/badge/skills/eaststarai/sanad-agent/sanad-client-tester/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.
<a href="https://agentmods.dev/skills/eaststarai/sanad-agent/sanad-client-tester"><img src="https://agentmods.dev/badge/skills/eaststarai/sanad-agent/sanad-client-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00038 | $0.04544 |
| Opus 5 | $0.00019 | $0.02272 |
| Sonnet 5 | $0.00008 | $0.00909 |
| Haiku 4.5 | $0.00004 | $0.00454 |
Grade A, and why
Sanad Client Tester 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 2d 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sanad Client Testing & Interactive Verification Protocol
This guide defines the unified interactive testing and verification protocol for client, designed to let AI agents verify interfaces, debug logic, and run integration tests inside isolated Git worktrees.
The CLI is platform-neutral, but it is not an accessibility crawler for arbitrary Flutter applications: the target Sanad Client must be launched through client/lib/driver_main.dart so the required Flutter Driver and Sanad service extensions are registered. sanad-dev ui owns desktop/worktree discovery. Mobile and web targets require a reachable explicit --vm-url (or VM_SERVICE_URL) and the same driver entry point.
1. Testing Methods & Priority Rules
Non-Negotiable Testing Rules
- Format & Analyze Single-Gate: Do not run tests before verifying that static analysis and formatting pass for the files/surface being changed.
- Scope-Based Automated Tests: Run the focused unit/widget tests that cover the changed behavior. Run the full fast suite only for broad/shared-surface changes.
- E2E By Scope Only: Run E2E or integration tests only when the change affects real socket behavior, local daemon connection states, app/bootstrap runtime integration, worktree port/runtime isolation, client/daemon contracts, or another system boundary that mocks cannot validate.
- Sequential Execution Only For Port-Binding Tests: Use
--concurrency=1only for E2E/integration tests that bind system ports or exclusive resources. Do not apply it to normal unit/widget/fast suites. - Clean Isolation: Run Unit and Widget tests locally without launching external servers or the local daemon.
- Desktop Interactive Last: Launch the Interactive UI Testing Protocol only when static tests cannot validate the behavior or when visual/runtime verification is explicitly needed.
Testing Priority Flowchart
graph TD
Start([Code Change Complete]) --> P1[1. Format & Analyze: fvm flutter analyze]
P1 -->|Pass| P2[2. Targeted Unit/Widget Tests]
P1 -->|Fail| Fix1[Fix Syntax & Lint Issues] --> P1
P2 -->|Pass| P3{Broad/shared surface?}
P2 -->|Fail| Fix2[Fix Logic & State Cubits] --> P2
P3 -->|Yes| P4[3. Full Fast Suite: fvm flutter test]
P3 -->|No| P5{Runtime/contract/port boundary?}
P4 -->|Pass| P5
P4 -->|Fail| Fix3[Fix Regressions] --> P4
P5 -->|Yes| P6[4. E2E/Integration Tests]
P5 -->|No| P7{Needs live UI verification?}
P6 -->|Pass| P7
P6 -->|Fail| Fix4[Fix E2E Integration Logic] --> P6
P7 -->|Yes| P8[5. Interactive UI Tests]
P7 -->|No| Success([Verify & Done])
P8 -->|Pass| Success
P8 -->|Fail| Fix5[Fix Interactive Flow / Hot Restart] --> P8
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.
- 2d ago Changed · +11 lines 81743ced67ca
- 7d ago Changed · +26 lines 60dec4803964
- 11d ago First seen · 273 lines · 38 tokens per session scan A 676f99d806e9
Sanad Client Tester is a skill published in the GitHub repository EastStarAI/sanad-agent (44 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 4,544 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 2026-08-30.
Other skills, from other repositories
flutter-testing
Covers Flutter testing across all three layers: unit tests (business logic, ViewModels, repositories), widget tests (UI rendering, interactions, golden regression), and integration/E2E tests (full app flows, native OS interactions). Use this skill when writing any Flutter test, setting up mocking with mocktail or…
flutter-testing
Write, fix, review, debug, and validate Flutter tests for apps, packages, and plugins. Use when adding unit tests, widget tests, integration tests, MethodChannel or plugin mocks, Mockito or mocktail test doubles, golden or accessibility checks, CI test commands, test failures, MissingPluginException, pump or…
flutter-mcp-toolkit-control
Drive a running Flutter app — tap, scroll, type, fill forms, hot-reload, navigate. Use when you need to interact with the UI.
testing
Use when writing or reviewing Flutter/Dart tests (unit, widget, golden), fixing flaky tests, adding coverage, or choosing between unit and widget tests.
flutter-mcp-cli-runtime-validation
Run Flutter MCP runtime validation from CLI in two steps (launch app, then run validate-runtime), including toolkit-extension gating, screenshot/layout capture, app error collection, optional reload verification, and retry handling for transient first-connect failures.
dev-testing
A testing guide that defines when to use unit, integration, API, and end-to-end tests. Unit tests check small pieces of code, while end-to-end tests check a full user flow.