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 | $0.00072 | $0.01478 |
| Opus 5.5 | $0.00029 | $0.00591 |
| Sonnet 5.5 | $0.00014 | $0.00296 |
| Haiku 4.5 | $0.00007 | $0.00148 |
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.
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.
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
fvmfor every Flutter or Dart operation. - Analyze before testing, then run focused unit/widget coverage; broaden only when the change surface requires it.
- Use
--concurrency=1only 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-devfor 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.
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.
- evals/evals.json 3.2 KB
- references/automated-testing.md 1.8 KB
- references/connection-switching.md 3.8 KB
- references/decision-layer-routing.md 18 KB
- references/interactive-ui-testing.md 4.7 KB
- references/jev-conversation-automation.md 4.2 KB
- references/multi-question-ui.md 1.3 KB
- references/runtime-and-worktrees.md 3.2 KB
- scripts/decision_layer/__init__.py 2.4 KB runs code
- scripts/decision_layer/__main__.py 540 B runs code
- scripts/decision_layer/actions.py 14 KB runs code
- scripts/decision_layer/brake.py 7.4 KB runs code
- scripts/decision_layer/bridge.py 2.0 KB runs code
- scripts/decision_layer/candidates.py 11 KB runs code
- scripts/decision_layer/cli.py 6.8 KB runs code
- scripts/decision_layer/escalation.py 2.3 KB runs code
- scripts/decision_layer/guard.py 10 KB runs code
- scripts/decision_layer/layer.py 18 KB runs code
- scripts/decision_layer/model.py 9.9 KB runs code
- scripts/decision_layer/modes.py 9.7 KB runs code
- scripts/decision_layer/observation.py 3.5 KB runs code
- scripts/decision_layer/smoke.py 10 KB runs code
- scripts/decision_layer/trace.py 4.8 KB runs code
- scripts/dual_brain_sanad_ui.py 3.1 KB runs code
- scripts/sanad_conversation_workflow.py 29 KB runs code
- tests/fixtures/labels.json 10 KB
- tests/fixtures/README.md 3.4 KB
- tests/fixtures/snapshots/01-conversation-idle.json 16 KB
- tests/fixtures/snapshots/02-conversation-search-open.json 16 KB
- tests/fixtures/snapshots/03-model-picker.json 22 KB
- tests/fixtures/snapshots/04-model-picker-filtered.json 20 KB
- tests/fixtures/snapshots/05-permission-mode-popup.json 16 KB
- tests/fixtures/snapshots/06-thinking-mode-popup.json 17 KB
- tests/fixtures/snapshots/07-device-switcher-popup.json 16 KB
- tests/fixtures/snapshots/08-settings-root.json 20 KB
- tests/fixtures/snapshots/09-settings-mcp-servers.json 19 KB
- tests/fixtures/snapshots/10-settings-skills.json 18 KB
- tests/fixtures/snapshots/11-settings-providers.json 25 KB
- tests/fixtures/snapshots/12-settings-device.json 19 KB
- tests/fixtures/snapshots/13-settings-workspace.json 20 KB
- tests/fixtures/snapshots/14-conversation-empty-session.json 14 KB
- tests/fixtures/snapshots/15-conversation-streaming.json 18 KB
- tests/fixtures/snapshots/16-ask-user-card.json 18 KB
- tests/fixtures/snapshots/17-ask-user-custom-input.json 18 KB
- tests/fixtures/snapshots/18-ask-user-question2.json 18 KB
- tests/fixtures/snapshots/19-conversation-after-ask-user.json 19 KB
- tests/fixtures/snapshots/20-permission-card.json 20 KB
- tests/fixtures/snapshots/21-permission-deny-comment.json 20 KB
- tests/fixtures/snapshots/22-conversation-after-deny.json 21 KB
- tests/fixtures/snapshots/23-conversation-search-query.json 23 KB
- tests/fixtures/snapshots/24-settings-profile.json 20 KB
- tests/test_decision_layer_brake.py 10 KB runs code
- tests/test_decision_layer_extractor.py 7.6 KB runs code
- tests/test_decision_layer_fixtures.py 5.4 KB runs code
- tests/test_decision_layer_guard.py 19 KB runs code
- tests/test_decision_layer_models.py 8.1 KB runs code
- tests/test_decision_layer_modes.py 7.0 KB runs code
- tests/test_decision_layer_provider.py 16 KB runs code
- tests/test_decision_layer_trace.py 6.0 KB runs code
- tests/test_sanad_conversation_workflow.py 8.2 KB runs code
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.
- 14d ago Changed · +2 lines 0e03216f8f53
- 15d ago Changed · +13 lines 33c285833ef3
- 16d ago Changed · +1 lines e7ea488cd495
- 1mo ago Changed · -260 lines · +34 tokens per session e65c7ea1463f
- 1mo ago Changed · +9 lines 02ef67a49e14
- 1mo ago Changed · -1 lines b0adc351fe9d
- 1mo ago Changed · +11 lines 81743ced67ca
- 2mo ago Changed · +26 lines 60dec4803964
- 2mo 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 (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.
Sanad Client Tester compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Sanad Client TesterEastStarAI/sanad-agent | Skill | 47 | yesterday | MIT | A | 72 | Claude Code, Codex |
| flutter-testingMADTeacher/mad-agents-skills | Skill | 112 | 6mo ago | MIT | A | 93 | Claude Code, Codex |
| flutter-testingPoorgramer-Zack/dart-expert-skills | Skill | 7 | 2mo ago | MIT | A | 137 | Claude Code, Codex |
| testingevanca/flutter-ai-rules | Skill | 669 | yesterday | MIT | A | 33 | Claude Code |
| flutter-mcp-toolkit-controlArenukvern/mcp_flutter | Skill | 395 | 20d ago | MIT | A | 38 | Claude Code |
| flutter-mcp-e2e-harnessArenukvern/mcp_flutter | Skill | 395 | 20d ago | MIT | A | 117 | Claude Code |
| flutter-mcp-cli-runtime-validationArenukvern/mcp_flutter | Skill | 395 | 20d ago | MIT | A | 52 | Claude Code |