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 skills add jggomez/expert-ai-developer-skills --skill flutter-senior-orchestrationgit clone --depth 1 https://github.com/jggomez/expert-ai-developer-skillsWrote 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/jggomez/expert-ai-developer-skills/flutter-senior-orchestration)<a href="https://agentmods.dev/skills/jggomez/expert-ai-developer-skills/flutter-senior-orchestration"><img src="https://agentmods.dev/badge/skills/jggomez/expert-ai-developer-skills/flutter-senior-orchestration/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/jggomez/expert-ai-developer-skills/flutter-senior-orchestration"><img src="https://agentmods.dev/badge/skills/jggomez/expert-ai-developer-skills/flutter-senior-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00103 | $0.03615 |
| Opus 5.5 | $0.00041 | $0.01446 |
| Sonnet 5.5 | $0.00021 | $0.00723 |
| Haiku 4.5 | $0.00010 | $0.00362 |
Grade A, and why
flutter-senior-orchestration 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 today.
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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flutter Senior Orchestration
Overview
The Flutter Senior Orchestration skill governs end-to-end delivery of Flutter and Dart applications across a 6-state Graph Engineering DAG: silent Cross-AI LLM Wiki memory restoration (context/memory/MEMORY.md), target-project AGENTS.md (<= 90 lines) integration, 3-Tier Dynamic Routing, Capability & Risk-Gated Dispatch in PLAN.md (<= 50 lines per feature), parallel TDD implementation, tiered review (Adversarial Review Committee), Fail-Honest E2E transparency, and milestone memory persistence across Claude Code and Google Antigravity.
When to Use
- Trigger Scenarios:
- Orchestrating Flutter features, multi-screen flows, widget refactors, state management migrations, 60/120fps jank fixes, or multi-platform store releases.
- Coordinating capability-gated discovery (
ui-ux-designer,flutter-architect), isolated parallelflutter-implementertracks, and tiered verification (flutter-reviewer,flutter-release-engineer,qa-tester).
- When NOT to Use:
- Pure backend tasks (
python-expert,database-migration-expert) or single-turn Q&A without code edits.
- Pure backend tasks (
Core Invariants & Artifact Line Budgets
- Zero Direct Dart Implementation: The orchestrator NEVER edits
.dartfiles (lib/,test/). Direct writes are restricted toPLAN.md, rootAGENTS.md, rootDESIGN.md,doc/adr/*.md,docs/(docs/<feature-name>/),.agents/, andcontext/memory/. - Automated Git Branch Governance & Scope Drift: Never work on
main,master,develop, ordev. At State 0, inspectgit symbolic-ref --short HEADand auto-branch (git checkout -b feat/<descriptive-slug>orfix/<slug>). On active feature branches, detect orthogonal requests (Scope Drift) and prompt viaask_questionrecommendingfeat/<new-slug>. - Target-Project
AGENTS.md+DESIGN.md+MEMORY.mdIntegration: In State 0 / State 5, verify rootAGENTS.md; if missing or if stack/commands/conventions changed, generate/update a concise rootAGENTS.md(<= 90 lines) linking executable commands (flutter analyze,flutter test), rootDESIGN.md, andcontext/memory/MEMORY.md. - Strict Conciseness Line Caps:
PLAN.mdfeature block<= 50 lines| RootAGENTS.md <= 90 lines| RootDESIGN.md <= 110 lines- Single discovery file
docs/<feature-name>/spec.md:## Product <= 50(product-analyst) |## Design <= 30(ui-ux-designer, screen delta only) |## Architecture <= 50(flutter-architect) adr-NNN-*.md <= 55 lines(only for a structural decision) |docs/<feature-name>/test-matrix.md <= 80 lines|docs/<feature-name>/evidence/*.png- No review report files:
flutter-reviewer,critic,challenger,e2e-blackbox-testerreturn their verdict in the final message (<= 50 lines: verdict, findings withfile:line, required fixes). - Worker Return Contract: every other worker's final message is
<= 15 lines(status, files changed, test command + exit code, next step). Never ask workers for long narratives.
- Fail-Honest E2E Transparency: If
e2e-blackbox-testerreturnsBLOCKEDorSKIPPED(e.g., mobile-only target without web, server couldn't start, Chromium unavailable), explicitly tell the user in the final summary: "Browser E2E was NOT executed (BLOCKED/SKIPPED): " — NEVER mask it as passed.
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.
- today First seen · 100 lines · 103 tokens per session scan A d2c1eb94b4d3
flutter-senior-orchestration is a skill published in the GitHub repository jggomez/expert-ai-developer-skills (30 stars, last pushed yesterday), licensed Apache-2.0. It adds 103 tokens to every session and 3,615 once invoked, about $0.0004 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 2026-11-06.
flutter-senior-orchestration compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| flutter-senior-orchestrationjggomez/expert-ai-developer-skills | Skill | 30 | yesterday | Apache-2.0 | A | 103 | Claude Code, Codex |
| user-contextXiaomiMiMo/MiMo-Code | Skill | 14k | yesterday | MIT | A | 86 | Codex |
| browserwing-executorMemTensor/MemOS | Skill | 12k | 2d ago | Apache-2.0 | A | 42 | Claude Code, Codex |
| obsidian-layout-adjustmentAr9av/obsidian-wiki | Skill | 3.7k | yesterday | MIT | A | 52 | Claude Code |
| ui-craftMemTensor/memmy-agent | Skill | 2.2k | yesterday | MIT | A | 86 | Claude Code, Codex |
| pneuma-preferencespandazki/pneuma-skills | Skill | 161 | yesterday | MIT | A | 100 | Claude Code, Codex |
| memoire-design-toolingmemi-design/memi | Skill | 50 | 2d ago | MIT | A | 51 | Claude Code, Codex |