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 commands/scarrillo/release/whattotestgit clone --depth 1 https://github.com/scarrillo/releaseWrote 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/commands/scarrillo/release/whattotest)<a href="https://agentmods.dev/commands/scarrillo/release/whattotest"><img src="https://agentmods.dev/badge/commands/scarrillo/release/whattotest.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 | $0.00010 | $0.00779 |
| Opus 5 | $0.00005 | $0.00390 |
| Sonnet 5 | $0.00002 | $0.00156 |
| Haiku 4.5 | $0.00001 | $0.00078 |
Grade A, and why
whattotest 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TestFlight WhatToTest Generator
Generate a WhatToTest document for TestFlight beta releases.
Model: Uses the model configured in release-plugin.model (see /release:changelog for model selection).
Instructions
-
Locate source content (in priority order):
- If called from /release:changelog: Use the
changelog-public.mdthat was just generated in this session. Do not re-analyze - derive directly from that file. - If called directly: Look for source content in this order:
changelog-public.mdin the project- Recent changelog files in the project
- Git commit history for recent changes
- Release notes or version documentation
- If called from /release:changelog: Use the
-
Check for existing WhatToTest files:
Search for existing WhatToTest files in
./TestFlight/, checking in this order:WhatToTest.en-US.txt(default)- Other locale variants (e.g.,
.de.txt,.fr.txt)
If existing file(s) found, use the same location and filename.
Check config for
release-plugin.whattotest.onExisting:- If
"prepend": Prepend new entry without asking - If
"replace": Replace content without asking - If
"ask"(default): Prompt the user: "WhatToTest file already exists. How should I handle it?"- Prepend new entry (keep history, newest at top) - Recommended
- Replace all (start fresh with only this release)
If no existing file found, create
./TestFlight/WhatToTest.en-US.txt. Create theTestFlight/folder if it doesn't exist. -
Generate WhatToTest content that is:
- Under 4000 characters total (hard limit — TestFlight rejects content exceeding this). Count characters before writing the file. If over, condense until it fits.
- No special characters — use only plain ASCII. Avoid smart quotes, em dashes, bullets (•), or other unicode characters. Use hyphens (-) for lists and straight quotes.
- Concise and actionable for testers
- Focused on what testers should specifically test
- Written in plain language (non-technical)
- Organized by feature area or priority
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 · 88 lines · 10 tokens per session scan A aac70b97836d
whattotest is a command published in the GitHub repository scarrillo/release (9 stars, last pushed 5mo ago), licensed MIT. It adds 10 tokens to every session and 779 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 2026-08-31.
Other commands, from other repositories
review-android
Guided Android code review workflow through context gathering, Android-specific review, and output.
app-store-audit
Run an enterprise pre submission compliance audit on an iOS or Android app against Apple App Store and Google Play rejection rules. Pass a project path or run from the project root.
build-verify
Run the full build / test / analyze / format verification pass for this Flutter app.
create-pr-from-staged-changes
You are helping to create a pull request following the iOS team's standard template.
apollo-status
Show the current Apollo removal migration progress.
ios-privacy
Prepare privacy labels, permissions, policy links, and data-use truth for iOS release.