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 rules/arenukvern/mcp_flutter/stewardgit clone --depth 1 https://github.com/Arenukvern/mcp_flutterWhat 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 | $0.00000 | $0.00235 |
| Opus 5 | $0.00000 | $0.00118 |
| Sonnet 5 | $0.00000 | $0.00047 |
| Haiku 4.5 | $0.00000 | $0.00023 |
Grade A, and why
steward 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 3d 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
You are operating in a repository governed by Skill Steward.
Do not run complex bash scripts manually. Use steward mcp or the underlying pipelines.
Available Pipelines:
- subagent_test: A test by subagent
- validate: Run all 11 repository contract checks and schema validations
- sync-skills: Regenerate skill assets from mcp_flutter skills
- web-showcase: Launch the Flutter test application showcase on macOS
Available Skills:
- flutter-mcp
- flutter-mcp-boundary-audit
- flutter-mcp-cli-runtime-validation
- flutter-mcp-toolkit-control
- flutter-mcp-toolkit-custom-tools
- flutter-mcp-toolkit-debug
- flutter-mcp-toolkit-dogfood-iterations
- flutter-mcp-toolkit-guide
- flutter-mcp-toolkit-inspect
- flutter-mcp-toolkit-intentcall-migration
- flutter-mcp-toolkit-maintain-macos
- flutter-mcp-toolkit-maintain-web
- flutter-mcp-toolkit-repo-maintainer
- flutter-mcp-toolkit-setup
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.
- 3d ago First seen · 30 lines · 235 tokens per session scan A 0491840dddd4
steward is a cursor rule published in the GitHub repository Arenukvern/mcp_flutter (372 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 235 tokens. 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 cursor rules, from other repositories
terradart
TerraDart shared project guide.
validation-harness
Validation harness — interfaces, adapters, cenários E2E.
project-core
Invariantes globais do laboratório Flutter + validation harness.
flutter-app
Convenções do app Flutter (lib/).
testing
Cursor rule "testing" from BlackLeg15/desafio_bloc_1, covering testing and cobertura existente.
best-practices
Flutter Best Practices - enforces current patterns when working with Flutter code.