Borrowing it
Nothing to install: this file belongs to mobile-next/mobilewright. 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/mobile-next/mobilewright/main/.claude/commands/release-mobilewright.mdgit clone --depth 1 https://github.com/mobile-next/mobilewrightWrote 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/mobile-next/mobilewright/release-mobilewright)<a href="https://agentmods.dev/commands/mobile-next/mobilewright/release-mobilewright"><img src="https://agentmods.dev/badge/commands/mobile-next/mobilewright/release-mobilewright/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/commands/mobile-next/mobilewright/release-mobilewright"><img src="https://agentmods.dev/badge/commands/mobile-next/mobilewright/release-mobilewright.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 | $0.00000 | $0.00870 |
| Opus 5.5 | $0.00000 | $0.00348 |
| Sonnet 5.5 | $0.00000 | $0.00174 |
| Haiku 4.5 | $0.00000 | $0.00087 |
Grade A, and why
release-mobilewright 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 23d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prepare a mobilewright release by updating CHANGELOG.md with the next patch version.
Steps
1. Verify version consistency
- Make sure you are currently on the main branch, otherwise stop.
- Make sure there are no staged or modified file, the checkout is clear. Otherwise, stop.
- Run
git tag --sort=-version:refname | head -1to get the latest git tag (e.g.v0.0.35) - Read the first line of
CHANGELOG.mdto extract the version there (e.g.## [0.0.35]) - If they do not match, stop and report the mismatch. Do not proceed.
2. Compute next version
- Strip the
vprefix from the latest tag, split on., increment the patch segment by 1 - Example:
v0.0.35→0.0.36
3. Collect changes since last tag
- Run
git log v<LAST_VERSION>..HEAD --onelineto list commits - For each commit, try to find an associated PR number:
- Look for
(#NNN)in the commit message, or - Run
gh pr list --state merged --search "<commit sha>" --json number,title,authorvia the GitHub API
- Look for
- For each PR found, fetch the author:
gh pr view <NNN> --repo mobile-next/mobilewright --json author --jq '.author.login'
4. Determine contributor credit
- Read
.github/CODEOWNERSto get the list of maintainer GitHub logins - For each change, if the PR author is not in the CODEOWNERS maintainers list, append:
thanks to [@<login>](https://github.com/<login>)
5. Format the CHANGELOG entry
Use the existing CHANGELOG.md format:
## [0.0.36] (YYYY-MM-DD)
* Feat: description ([#NNN](https://github.com/mobile-next/mobilewright/pull/NNN))
* Fix: description ([#NNN](https://github.com/mobile-next/mobilewright/pull/NNN)), thanks to [@login](https://github.com/login)
- Use today's date for the release date
- Capitalise the type prefix (
Feat,Fix,Chore, etc.) from the conventional commit prefix - Omit chore/ci/docs commits that are not user-facing unless they are significant
- Prepend the new entry at the top of CHANGELOG.md, above the previous
## [...]line
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.
- 23d ago Changed · +20 lines 76f999f73eeb
- 2mo ago First seen · 60 lines · 0 tokens per session scan A 0ff0f4eb9c4e
release-mobilewright is a command published in the GitHub repository mobile-next/mobilewright (466 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 870 tokens. 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.
release-mobilewright compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| release-mobilewrightmobile-next/mobilewright | Command | 466 | 5d ago | Apache-2.0 | A | 0 | Claude Code |
| copilotkelvinkosbab/AppBootstrapAI | Command | 8 | today | MIT | A | 19 | Claude Code |
| claudekelvinkosbab/AppBootstrapAI | Command | 8 | today | MIT | A | 19 | Claude Code |
| cursorkelvinkosbab/AppBootstrapAI | Command | 8 | today | MIT | A | 0 | Claude Code |
| feature-buildahmed3elshaer/everything-claude-code-mobile | Command | 66 | 4mo ago | MIT | A | 45 | Claude Code |
| feature-testahmed3elshaer/everything-claude-code-mobile | Command | 66 | 4mo ago | MIT | A | 31 | Claude Code |
| feature-verifyahmed3elshaer/everything-claude-code-mobile | Command | 66 | 4mo ago | MIT | A | 24 | Claude Code |