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/analyze-github-flakenpx skills add flutter/flutter --skill analyze-github-flakegit clone --depth 1 https://github.com/flutter/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 | $0.00042 | $0.01089 |
| Opus 5 | $0.00021 | $0.00544 |
| Sonnet 5 | $0.00008 | $0.00218 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
analyze-github-flake scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl 'https://cr-buildbucket.appspot.com/prpc/buildbucket.v2.Builds/GetBuild' \ How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flake analysis instructions
Rules You should not modify ANY files - you are only to provide an analysis of why the specific check is flaking. You should only look at the issue body, as well as comments containing links to additional builds. You should not attempt to solve the flakes or pinpoint root causes inside of flutter/, just provide a high level summary of what is going on and bucket the failures into distinct types.
Collecting the list of failing builds and obtaining the logs
Github issue urls take the form of https://github.com/flutter/flutter/issues/. Where issue-number is a number.
Get information about the issue by using gh issue view <issue-number> --repo flutter/flutter --json=author,body,id,labels,number,state,title,url
For example to find information about the issue https://github.com/flutter/flutter/issues/174116 you can call gh issue view 174116 --repo flutter/flutter --json=author,body,id,labels,number,state,title,url
At this point there are two possible cases. If the issue
- Is filed by fluttergithubbot
- Has a title of the format "<ci.yaml target> is X% flaky" Then it is of the type we are looking to analyze. If it is not, you should short circuit here, either notifying the user that the issue is not filed by the github flake bot (if they directly asked for the skill to be invoked) or otherwise continue with your previous work (if they did not).
If the previous conditions are met, the title will contain the name of the flaking check, and the body will contain urls which link to instances where the check failed or flaked, each on a new line, directly after "Flaky builds:". You should also inspect the comments and find each comment made by "login": "fluttergithubbot", and extract the urls from there as well (the format will be the same, with an example flake at the top, and the full list immediately after the "Flaky builds:" header).
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.
- yesterday First seen · 70 lines · 42 tokens per session scan A 4b5d684f5e14
analyze-github-flake is a skill published in the GitHub repository flutter/flutter (178,720 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 42 tokens to every session and 1,089 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
argent-device-interact
Interact with an iOS simulator, Android emulator, or Chromium (CDP) app using argent MCP tools. Use when tapping UI elements, performing gestures, scrolling/swiping, typing text, pressing hardware buttons, launching apps, opening URLs, taking screenshots, waiting for an element to appear or disappear, or checking…
argent-settings-permissions
Grant, deny, or reset an app's runtime permissions (camera, microphone, photos, contacts, notifications, calendar, location, location-always, media-library, motion, reminders) on an iOS simulator or Android device using the argent settings-permissions tool - without navigating the system Settings UI. Use when the…
argent-lens
Propose multiple visual design variants for on-screen elements and let the human pick in the Argent Lens window. Use when the user asks for design alternatives / options / A-B choices for a screen or component, or any time you have produced more than one candidate look for an element and want a human decision before…
argent-screenshot-diff
Compare saved or live app screenshots with the argent screenshot-diff tool. Use when testing visual regressions, before/after UI comparisons, screenshot diff checks, visible layout, spacing, color, typography, clipping, overflow, text rendering, or image/icon rendering changes.
truesheet-usage
Consumer-side guide for integrating @lodev09/react-native-true-sheet into a React Native app. Use this skill whenever the user wants to add, configure, control, or debug a bottom sheet using TrueSheet — including ref-based sheets, named global sheets, web support with TrueSheetProvider/useTrueSheet, React Navigation…
update-store
ストア情報の更新自動化 — スクリーンショット撮影（シミュレーター × モック画面 × Marionette MCP）とメタデータテキスト更新。ストア更新、スクショ更新、App Store / Google Play のメタデータ更新、リリースノート作成の際に使用すること。.