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.
npx agentmods add agents/timzaak/web-dev-skills/flutter-demo-devgit clone --depth 1 https://github.com/timzaak/web-dev-skillsWhat 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 | $0.00020 | $0.00317 |
| Opus 5 | $0.00010 | $0.00159 |
| Sonnet 5 | $0.00004 | $0.00063 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
flutter-demo-dev 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.
What it actually says
Flutter Demo Dev
先读目标项目 AGENTS.md、pubspec.yaml、pubspec.lock、相关用户故事和设计，再读：
${CLAUDE_PLUGIN_ROOT}/protocols/flutter-demo-run-repair-contract.md${CLAUDE_PLUGIN_ROOT}/guides/flutter/demo-testing.md${CLAUDE_PLUGIN_ROOT}/guides/flutter/integration-testing.md
边界
- 在
patrol_test/<domain>/<story>_test.dart编写按 US ID 追踪的 Android 用户故事演示。 - 使用生产 composition root 或 Demo entrypoint；只能通过环境配置切换测试环境，不得注入 Provider fake 代替真实流程。
- 使用稳定 Key/Semantics，关键结果断言持久页面或业务状态；禁止
sleep、无断言流程和生产数据。 - 有外部环境时复用项目自己的成对
scripts/flutter-demo-start.py/flutter-demo-stop.py；没有后端的 App 不新增空环境脚本。 - 测试 authoring 与集中 runner 分离。修复运行失败时返回
task_completion和最小tests_to_run。
输出遵循 ${CLAUDE_PLUGIN_ROOT}/protocols/agent-task-output-contract.md。
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 First seen · 25 lines · 20 tokens per session scan A ca0650115dca
flutter-demo-dev is an agent published in the GitHub repository timzaak/web-dev-skills (69 stars, last pushed 4d ago), licensed Apache-2.0. It adds 20 tokens to every session and 317 once invoked, about $0.0001 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 agents, from other repositories
test-engineer
Android QA engineer specialized in test strategy, test design, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.
e2e-verifier
FlutterアプリのE2E動作検証エージェント。MCP（dart-mcp + Marionette）を使い、シミュレーター上でUI操作・検証を行う。mobile-automationスキルから呼び出される。.
e2e-testing
pnpm expo run:ios pnpm expo run:android.
playground-testing
Rozenite DevTools plugins. Every screen exists to trigger one plugin behavior; DevTools is where you observe the result.
project-explorer
Read all project configuration files and source code to build a structured app-profile.json that captures the app's capabilities, permissions, dependencies, and usage patterns. This profile becomes the input for the Guideline Auditor.
fixer
Apply code-level fixes for user-approved FAIL items. Given a list of failed guidelines the developer wants to fix, implement the necessary changes to Swift/Objective-C source files, configuration files, and metadata.