sanad-agent: Skill for Claude Code

.agents/skills/sanad-client-tester/SKILL.md

Sanad Client Tester is a skill for Claude Code, Codex from EastStarAI/sanad-agent. It costs 72 tokens per session (1,478 once invoked), scanned A, original, MIT.

A testing procedure for the Sanad Flutter client, a cross-platform app built with Dart. It covers code-level tests, interface tests, end-to-end checks, and agent-driven UI verification through the Dart VM Service.

In plain words
What is it for?
Testing Sanad client logic and screens, running focused unit or widget tests, checking real socket behavior with end-to-end tests, and inspecting the app through its required driver entry point.
Why use it?
It helps verify that client changes work at the right level without running unnecessary broad tests. It also checks formatting and static analysis before tests.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; installed under .agents/ (shared by several agents).

This is EastStarAI/sanad-agent's own configuration. It tells Claude Code and Codex how to work on sanad-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sanad-agent configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/EastStarAI/sanad-agent/main/.agents/skills/sanad-client-tester/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/EastStarAI/sanad-agent

Made for: Claude Code, Codex.

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 Sanad Client Tester

README.md
[![agentmods](https://agentmods.dev/badge/skills/eaststarai/sanad-agent/sanad-client-tester/github.svg)](https://agentmods.dev/skills/eaststarai/sanad-agent/sanad-client-tester)
Your own site
<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.

agentmods 80×15 button for Sanad Client Tester

Your own site · 80×15
<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>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,478 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00072 $0.01478
Opus 5.5 $0.00029 $0.00591
Sonnet 5.5 $0.00014 $0.00296
Haiku 4.5 $0.00007 $0.00148

Measured 14d ago against content hash 0e03216f8f53, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 14d ago.

The scan reads SKILL.md. This mod also ships 26 executable files (scripts/decision_layer/__init__.py, scripts/decision_layer/__main__.py, scripts/decision_layer/actions.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/sanad-client-tester/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.

Sanad Client Tester

Use this skill to select and execute the smallest reliable verification boundary for the Sanad Flutter Client. The main file owns invariants and routing only; load the focused reference that matches the task instead of reading every procedure.

Non-negotiable invariants

  • Use fvm for every Flutter or Dart operation.
  • Analyze before testing, then run focused unit/widget coverage; broaden only when the change surface requires it.
  • Use --concurrency=1 only for tests that bind ports or exclusive resources.
  • Keep successful analyzer and test output to the final five lines while preserving exit status through pipefail; rerun only a failure unfiltered.
  • Use sanad-dev for managed runtime discovery and control. Never infer ownership from process age, directory naming, or a hardcoded port.
  • Before a UI action, inspect current state and resolve a unique stable key. Do not fall back to coordinates while a keyed target can be added or discovered.
  • Treat create, send, delete, submit, and similar effects as one-shot phases. Never retry an ambiguous irreversible action automatically.
  • Wait on lifecycle or UI events rather than snapshot/model polling, then verify the resulting state deterministically.
  • Do not stop, restart, or mutate a runtime not proven to be owned by the current worktree. Runtime source switching requires explicit user authorization under the repository contract.
  • Keep logs bounded and free of secrets or entered values.

Canonical conversation fast path

When a request fits scripts/sanad_conversation_workflow.py and supplies its required device, conversation, provider/model, message, and return inputs, load only references/jev-conversation-automation.md and execute the runner immediately. Do not run separate sanad-dev status, snapshot, find, log reads, --help, or full jev-dual-brain-automation skill loading first. The runner's internal ownership resolution, snapshot, exact-key admission, one-shot phase ledger, event waits, Jev call, and return verification are the preflight and execution boundary.

Read the full file on GitHub · 74 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 14d ago Changed · +2 lines 0e03216f8f53
  2. 15d ago Changed · +13 lines 33c285833ef3
  3. 16d ago Changed · +1 lines e7ea488cd495
  4. 1mo ago Changed · -260 lines · +34 tokens per session e65c7ea1463f
  5. 1mo ago Changed · +9 lines 02ef67a49e14
  6. 1mo ago Changed · -1 lines b0adc351fe9d
  7. 1mo ago Changed · +11 lines 81743ced67ca
  8. 2mo ago Changed · +26 lines 60dec4803964
  9. 2mo ago First seen · 273 lines · 38 tokens per session scan A 676f99d806e9

Subscribe to this mod's changes

Sanad Client Tester is a skill published in the GitHub repository EastStarAI/sanad-agent (47 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 1,478 once invoked, about $0.0003 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 2026-08-30.

Related

Sanad Client Tester compared with skills from other repositories

Sanad Client Tester next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Sanad Client TesterEastStarAI/sanad-agentSkill47yesterdayMITA72Claude Code, Codex
flutter-testingMADTeacher/mad-agents-skillsSkill1126mo agoMITA93Claude Code, Codex
flutter-testingPoorgramer-Zack/dart-expert-skillsSkill72mo agoMITA137Claude Code, Codex
testingevanca/flutter-ai-rulesSkill669yesterdayMITA33Claude Code
flutter-mcp-toolkit-controlArenukvern/mcp_flutterSkill39520d agoMITA38Claude Code
flutter-mcp-e2e-harnessArenukvern/mcp_flutterSkill39520d agoMITA117Claude Code
flutter-mcp-cli-runtime-validationArenukvern/mcp_flutterSkill39520d agoMITA52Claude Code