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 skills/flutter/flutter-intellij/triagenpx skills add flutter/flutter-intellij --skill triagegit clone --depth 1 https://github.com/flutter/flutter-intellijWrote 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/flutter/flutter-intellij/triage)<a href="https://agentmods.dev/skills/flutter/flutter-intellij/triage"><img src="https://agentmods.dev/badge/skills/flutter/flutter-intellij/triage.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.00318 |
| Opus 5 | $0.00013 | $0.00159 |
| Sonnet 5 | $0.00005 | $0.00064 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
triage-helper 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
When a user asks for help in the CLI:
- Find the latest open issues in the https://github.com/flutter/flutter-intellij/ repo that don't have a priority label.
- If you encounter authentication issues, guide the user to check their
github-mcp-serversetup orgh auth statusdepending on available tools. - Reference
docs/Triaging.mdfor detailed setup instructions. - Consider the most recently updated issues first. Start presenting issues one at a time to the user, with the issue URL and other relevant information.
- For each issue, give suggestions such as:
- Close the issue if it's not relevant anymore (e.g. it's been fixed, the code it's referencing is outdated, etc.)
- Suggest how to reproduce if it looks like it may be easy to reproduce locally
- Ask for a reproduction with a small project if reproduction may be hard locally
- Ask for more information and apply a waiting for response label
- Note a code pointer for the issue if it could be a good first issue for an external contributor
- Suggest a priority and other labels that may be relevant along with reasoning for the priority
- Then wait for user feedback before continuing on to the next issue.
Avoid executing tasks on GitHub directly, such as making comments, applying labels, or closing issues.
There is additional context on our issue triage process in docs/Triaging.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.
- 3d ago First seen · 22 lines · 26 tokens per session scan A 1e680800adb1
triage-helper is a skill published in the GitHub repository flutter/flutter-intellij (2,013 stars, last pushed 2d ago), licensed BSD-3-Clause. It adds 26 tokens to every session and 318 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 skills, from other repositories
shadcn-ui-flutter
A comprehensive Flutter UI library inspired by shadcn/ui. Provides high-quality, customizable, and accessible components including Buttons, Cards, Forms, and more. Use this skill when building Flutter UIs, implementing design systems, or needing specific component usage examples.
flutter-upgrade
Flutter SDKバージョンアップグレード対応。新バージョンのリリースノート・Breaking Changes調査、コードベース影響分析、mise/CI/Shorebird含むプロジェクト全体の対応タスクリスト作成と実行。「Flutterアップグレード」「Flutter X.Y.Zがリリースされた」「Flutter最新化」「Flutter更新」と言われたとき、またはFlutterの新バージョンについて言及されたときに使用する。.
release-bridge
Bridge Server のリリース（バージョンbump + CHANGELOG + タグ → GH Actions で npm publish）.
web-preview
Flutter Web版をビルド → サーバー起動 → Playwright でアクセス確認 → URLをユーザーに案内する。.
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
code-review
Use when asked to review a PR, MR, branch, or diff, audit changed files, or check code quality.