Update Homebrew cask install command

[SSakutaro]

Summary

• Update the README Homebrew cask command to use the official codexbar cask.

Context

• Follows up on docs: brew official cask #293, which proposed the same README change.
• docs: brew official cask #293 was closed as already reflected in current main, but README still points to steipete/tap/codexbar for the macOS cask install command.

Verification

• git diff --check

Docs-only change; build/tests not run.

[Copilot]

Pull request overview

Note

Copilot was unable to run its full agentic suite in this review.

Updates installation instructions to use the standard Homebrew cask name instead of a custom tap, simplifying setup for users.

Changes:

• Replace brew install --cask steipete/tap/codexbar with brew install --cask codexbar

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[clawsweeper]

Codex review: needs real behavior proof before merge. Reviewed May 27, 2026, 7:24 AM ET / 11:24 UTC.

Summary
The PR changes the README Homebrew cask install command from brew install --cask steipete/tap/codexbar to brew install --cask codexbar.

Reproducibility: yes. The compatibility problem is source-verifiable from the PR diff plus Homebrew cask metadata showing the default codexbar cask has an Arm 64-bit architecture requirement.

Review metrics: 1 noteworthy metric.

• Changed surface: 1 docs file, +1/-1. The PR changes only the primary README Homebrew install command, so architecture and fallback nuance must be handled in or near that docs line.

Merge readiness
Overall: 🧂 unranked krab
Proof: 🌊 off-meta tidepool
Patch quality: 🧂 unranked krab
Result: blocked by patch quality or review findings.

Overall follows the weaker of proof and patch quality, so missing proof can cap an otherwise strong patch.

Rank-up moves:

• Preserve or document the tap fallback/Intel path in README.md.
• Keep official-cask wording aligned with the current arm64 Homebrew cask requirement.

Risk before merge

• Merging as-is could route Intel macOS users from a tap cask path that is not arm64-gated to the default Homebrew cask that currently declares an arm64 requirement.
• The one-line README change would leave nearby install surfaces inconsistent, including the README badge and checked-in site text that still point at steipete/tap/codexbar.

Maintainer options:

1. Preserve the compatible install path (recommended)
   Before merge, keep steipete/tap/codexbar as the fallback or Intel-compatible Homebrew command, or explicitly label the official cask command as Apple Silicon-only.
2. Make Homebrew Apple Silicon-only
   Maintainers can intentionally document only the official cask, but the README should then state that Homebrew installs are Apple Silicon-only and point Intel users at GitHub Releases.

Copy recommended automerge instruction

@clawsweeper automerge

Special instructions:
Preserve the tap cask as the Intel/fallback Homebrew path or qualify `brew install --cask codexbar` as Apple Silicon-only, and keep README badge/text consistent; do not edit CHANGELOG.md.

Next step before merge
The repair is narrow and mechanical: update README.md so the official cask command does not remove or obscure the compatible tap/fallback path.

Security
Cleared: No concrete security or supply-chain regression was found; the diff is a README-only install-command change and the blocker is compatibility.

Review findings

• [P1] Preserve the Intel-compatible Homebrew path — README.md:35

Review details

Best possible solution:

Make the README install guidance architecture-aware: either keep the tap command as primary/fallback, or label brew install --cask codexbar as Apple Silicon-only and align adjacent README/site install text.

Do we have a high-confidence way to reproduce the issue?

Yes. The compatibility problem is source-verifiable from the PR diff plus Homebrew cask metadata showing the default codexbar cask has an Arm 64-bit architecture requirement.

Is this the best way to solve the issue?

No. Replacing the command alone is not the best fix; the maintainable docs path is to preserve the tap/fallback command or make the official cask's Apple Silicon-only scope explicit.

Full review comments:

• [P1] Preserve the Intel-compatible Homebrew path — README.md:35
  This sends every README Homebrew user to the default codexbar cask, but that cask currently requires Arm 64-bit architecture. Intel users who could use the existing tap command would be given a command Homebrew rejects, while the README still says only macOS 14+ is required. Please keep the tap command as a fallback or label the default cask as Apple Silicon-only. (formulae.brew.sh)
  Confidence: 0.94

Overall correctness: patch is incorrect
Overall confidence: 0.94

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against 83ed8e405541.

Label changes

Label changes:

• add P2: The PR is a small docs change, but it affects the install path for a supported macOS user segment.
• add merge-risk: 🚨 compatibility: The proposed command can fail for existing Intel users because the default cask is arm64-only while the current tap path is not shown with that gate.
• add rating: 🧂 unranked krab: Overall readiness is 🧂 unranked krab; proof is 🌊 off-meta tidepool and patch quality is 🧂 unranked krab.
• add status: ⏳ waiting on author: ClawSweeper has contributor-facing work open and is waiting for author action. Not applicable: Every changed file is under docs/README scope, so the external real-behavior proof gate does not apply.

Label justifications:

• P2: The PR is a small docs change, but it affects the install path for a supported macOS user segment.
• merge-risk: 🚨 compatibility: The proposed command can fail for existing Intel users because the default cask is arm64-only while the current tap path is not shown with that gate.
• rating: 🧂 unranked krab: Overall readiness is 🧂 unranked krab; proof is 🌊 off-meta tidepool and patch quality is 🧂 unranked krab.
• status: ⏳ waiting on author: ClawSweeper has contributor-facing work open and is waiting for author action. Not applicable: Every changed file is under docs/README scope, so the external real-behavior proof gate does not apply.

Evidence reviewed

Acceptance criteria:

• git diff --check
• rg -n "brew install --cask|Homebrew|Apple Silicon|steipete/tap/codexbar|--cask codexbar" README.md docs/index.html docs/releasing-homebrew.md

What I checked:

• Repository policy read: AGENTS.md was present and read in full; its docs/test/release-surface guidance was applied to this docs-only PR review. (AGENTS.md:1, 83ed8e405541)
• Current README install guidance: Current main lists macOS 14+ as the requirement and uses brew install --cask steipete/tap/codexbar for the Homebrew app install command. (README.md:35, 83ed8e405541)
• PR diff: The submitted diff changes only README.md line 35, replacing the tap-qualified cask with the default codexbar cask. (README.md:35, 08a7ef4a9a19)
• Official cask metadata: Homebrew's public cask page lists brew install --cask codexbar but also lists an Arm 64-bit architecture requirement, and the JSON API currently reports depends_on.arch as arm64. (formulae.brew.sh)
• Tap cask comparison: The current steipete/homebrew-tap cask fetched during review uses the same universal release zip and macOS Sonoma requirement but does not show the official cask's arm64-only gate.
• Public site install language: The checked-in site still presents the tap command and explicitly distinguishes universal GitHub Releases from Apple Silicon Homebrew installs. (docs/index.html:94, 83ed8e405541)

Likely related people:

• steipete: Recent README and Homebrew release-doc history points to steipete as the primary current owner for distribution/install documentation and release automation. (role: recent area contributor; confidence: high; commits: 83ed8e405541, 7e97d2b27ce5, 29cb71e88d81; files: README.md, docs/releasing-homebrew.md, docs/index.html)
• ratulsarna: ratulsarna handled the earlier related Homebrew cask docs PR and also appears in recent README documentation history, so they are useful context for the repeated request. (role: adjacent reviewer; confidence: medium; commits: c40deb9a6b0b; files: README.md)

What the crustacean ranks mean

• 🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
• 🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
• 🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
• 🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
• 🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
• 🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
• 🌊 off-meta tidepool: rating does not apply to this item.

Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics.

How this review workflow works

• ClawSweeper keeps one durable marker-backed review comment per issue or PR.
• Re-runs edit this comment so the latest verdict, findings, and automation markers stay together instead of adding duplicate bot comments.
• A fresh review can be triggered by eligible @clawsweeper re-review comments, exact-item GitHub events, scheduled/background review runs, or manual workflow dispatch.
• PR/issue authors and users with repository write access can comment @clawsweeper re-review or @clawsweeper re-run on an open PR or issue to request a fresh review only.
• Maintainers can also comment @clawsweeper review to request a fresh review only.
• Fresh-review commands do not start repair, autofix, rebase, CI repair, or automerge.
• Maintainer-only repair and merge flows require explicit commands such as @clawsweeper autofix, @clawsweeper automerge, @clawsweeper fix ci, or @clawsweeper address review.
• Maintainers can comment @clawsweeper explain to ask for more context, or @clawsweeper stop to stop active automation.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 08a7ef4a9a

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

[chatgpt-codex-connector]

Preserve Intel Homebrew install path

For Intel users on macOS 14+, this new command resolves to the Homebrew/homebrew-cask codexbar cask, whose current metadata has depends_on arch: :arm64; Homebrew will reject the install before downloading the universal release. The previous tap cask does not declare that arm64-only constraint, so this README change removes the only Homebrew install path that works for Intel Macs despite the Requirements section still saying only macOS 14+ is needed.

Useful? React with 👍 / 👎.

[SSakutaro]

@copilot
@clawsweeper
@chatgpt-codex-connector

I opened a Homebrew/homebrew-cask PR to fix that here:

Homebrew/homebrew-cask#266464

I also verified this on an Intel Mac:

• HOMEBREW_NO_INSTALL_FROM_API=1 brew install --cask codexbar
• file /Applications/CodexBar.app/Contents/MacOS/CodexBar
• file /Applications/CodexBar.app/Contents/Helpers/CodexBarCLI
• brew uninstall --cask codexbar

Both CodexBar and CodexBarCLI are universal binaries with x86_64 and arm64 slices, so once the Homebrew cask PR lands, brew install --cask codexbar should work for Intel Macs too.

[chatgpt-codex-connector]

To use Codex here, create a Codex account and connect to github.

[Copilot]

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated 1 comment.