Borrowing it
Nothing to install: this file belongs to ZingerLittleBee/Heeler. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ZingerLittleBee/Heeler/main/.claude/skills/testflight-beta/SKILL.mdgit clone --depth 1 https://github.com/ZingerLittleBee/HeelerWrote 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/zingerlittlebee/heeler/testflight-beta)<a href="https://agentmods.dev/skills/zingerlittlebee/heeler/testflight-beta"><img src="https://agentmods.dev/badge/skills/zingerlittlebee/heeler/testflight-beta/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/zingerlittlebee/heeler/testflight-beta"><img src="https://agentmods.dev/badge/skills/zingerlittlebee/heeler/testflight-beta.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 | $0.00088 | $0.01115 |
| Opus 5.5 | $0.00035 | $0.00446 |
| Sonnet 5.5 | $0.00018 | $0.00223 |
| Haiku 4.5 | $0.00009 | $0.00112 |
Grade A, and why
testflight-beta 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 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.
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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TestFlight external testing
Testers in the external group get a build only after it joins the group and passes Beta App Review. They read its What to Test, so the notes cover every change since the build they have now. Commands and credentials are documented in releasing.md.
1. Pick the build
Use the tag the maintainer names. Otherwise use the newest
git ls-remote --tags origin 'refs/tags/builds/*' tag. make release-status TAG=…
must show "state": "valid". If it doesn't, report the state and stop: CI is
still uploading, or the run needs make testflight-retry.
2. Collect the entries
Run make testflight-notes TAG=…. It prints the changelog entries that are new
since the build the Public Beta group has now. If it asks for SINCE, ask the
maintainer which build the testers last received.
3. Write the notes
Turn every entry into tester notes, or drop it on purpose. Drop only entries that change nothing in the app, such as the website, docs site or CI.
- The sections are New, Improved and Fixed (新增, 改进, 修复), from Added, Changed and Fixed. Leave out a section that has no lines.
- Give each thing a tester can try its own line. Split a long entry into one line per action or behaviour.
- Lead with what to do and where: "tap + then Paste Image".
- Write each control's name in English, exactly as the app shows it, in both
languages. Check every name against the strings in
Sources/, because CHANGELOG sometimes paraphrases them. - Keep any "Update the Heeler plugin to X on the Host" requirement.
- Use plain text with
-bullets and a blank line between sections. Write the English, then the Chinese, in one text under 4000 characters: Test Information has onlyen-US, so every tester reads both. - Write the Chinese as natural Simplified Chinese. Translate tap as 轻点, touch and hold as 长按, and Composer as 输入框.
An approved build's notes, abridged, are the reference:
New
- Paste an image into a message: tap + then Paste Image, or paste straight into the Composer.
- Chat shows images that Agents read or create as thumbnails. Tap one to zoom.
- Touch and hold an Agent on a By Workspace card to start a New Agent in the same Workspace and folder.
- Browse Directories hides dot folders. Tap the eye button to show them.
Improved
- The Shell Terminal input row moves in step with the keyboard.
- While Chat waits for a conversation, Show Agent Terminal and Check Again sit side by side, and Check Again shows a spinner.
Fixed
- Codex's folder access prompt now appears in Chat as a card with Trust and continue and Quit.
- iPhone Duo: Back, Show Chat / Show Agent Terminal and More now sit in the side controls.
新增
- 在消息里粘贴图片:轻点 + 再选 Paste Image,或直接粘贴到输入框。
- Chat 会以缩略图显示 Agent 读取或生成的图片,轻点可放大查看。
- 在 By Workspace 卡片上长按某个 Agent,可在同一 Workspace 和目录下新建 Agent。
- Browse Directories 默认隐藏以点开头的文件夹,轻点眼睛按钮可显示。
改进
- Shell Terminal 的输入行跟随键盘同步升降。
- Chat 等待对话时,Show Agent Terminal 和 Check Again 并排显示,Check Again 会显示加载动画。
修复
- Codex 的文件夹访问提示现在会在 Chat 中显示为卡片,提供 Trust and continue 和 Quit。
- iPhone Duo:Back、Show Chat / Show Agent Terminal 和 More 移到了侧边系统控件中。
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 · 92 lines · 88 tokens per session scan A 0a1206f808e6
testflight-beta is a skill published in the GitHub repository ZingerLittleBee/Heeler (776 stars, last pushed yesterday), licensed Apache-2.0. It adds 88 tokens to every session and 1,115 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.
testflight-beta compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| testflight-betaZingerLittleBee/Heeler | Skill | 776 | yesterday | Apache-2.0 | A | 88 | Claude Code |
| verify-vibebuddysemantic-craft/iOS-vibebuddy | Skill | 92 | 24d ago | MIT | C | 77 | Claude Code |
| analyzing-ios-app-security-with-objectionmukul975/Anthropic-Cybersecurity-Skills | Skill | 36k | 2mo ago | Apache-2.0 | A | 49 | Claude Code |
| ios-simulator-skillconorluddy/ios-simulator-skill | Skill | 1.3k | yesterday | MIT | A | 106 | Claude Code, Codex |
| argent-tv-interactsoftware-mansion/argent | Skill | 3.2k | yesterday | Apache-2.0 | A | 107 | Claude Code, Codex |
| mastgChiChou/grapefruit | Skill | 1.4k | 10d ago | MIT | A | 53 | Claude Code, Codex |
| figma-a11y-annotationscvs-health/ios-swiftui-accessibility-techniques | Skill | 388 | yesterday | Apache-2.0 | A | 110 | Claude Code, Codex |