docs: add Stream Deck integration

[lenadweb]

This adds AI Usage Limits to the README’s integrations list.

It’s a macOS Stream Deck plugin that displays a selected CodexBar provider, account, and usage metrics on Stream Deck keys and Stream Deck+ dials, using the local codexbar serve API. CodexBar continues to handle provider configuration, authentication, and data refresh.

Docs-only change, happy to adjust the wording or placement if you’d prefer.

[clawsweeper]

🦞👀
ClawSweeper picked this up.

Pull request received. I will update this pull request when review starts.

[clawsweeper]

Codex review: needs real behavior proof before merge. Reviewed August 19, 2026, 1:48 AM ET / 05:48 UTC.

ClawSweeper review

What this changes

The PR adds AI Usage Limits, a macOS Stream Deck plugin using CodexBar’s local service API, to the README integrations list.

Merge readiness

⚠️ Ready for maintainer review - 2 items remain

Keep open for normal merge review. The docs-only addition is consistent with the existing external-integration list and CodexBar’s documented local service API; no patch defect was found.

Priority: P3
Reviewed head: e5d69d8b4b3343d5b1b76f95c57eba0e28f34f83

Review scores

Measure	Result	What it means
Overall readiness	🐚 platinum hermit (4/6)	A focused documentation update consistent with the documented local integration surface.
Proof confidence	🌊 off-meta tidepool	Not applicable: This is a docs-only PR, so external runtime proof is not required.
Patch quality	🐚 platinum hermit (4/6)	No actionable review findings were identified.

Verification

Check	Result	Evidence
Real behavior	Not applicable	Not applicable: This is a docs-only PR, so external runtime proof is not required.
Evidence reviewed	4 items	Scoped README diff: The branch adds one integration-list entry and changes no runtime code, dependencies, or configuration. Supported integration boundary: Current CLI documentation defines codexbar serve as a foreground HTTP server for usage and cost JSON, a dashboard snapshot, and a web UI; the default host is loopback. Comparable README convention: The adjacent existing entry documents another third-party status-bar integration built on codexbar serve or the bundled CLI.
Findings	None	None.
Security	None	None.

How this fits together

CodexBar gathers provider usage data and exposes it through the local codexbar serve HTTP service. External desktop integrations can consume that service to display account and usage information while CodexBar retains provider setup and refresh ownership.

flowchart LR
  A[Provider accounts] --> B[CodexBar]
  B --> C[Local serve API]
  C --> D[Stream Deck plugin]
  D --> E[Keys and dials]

Loading

Before merge

• Add real behavior proof - Not applicable: This is a docs-only PR, so external runtime proof is not required.
• Complete next step (P2) - The patch has no mechanical repair item and only needs routine maintainer merge review.

Agent review details

Security

None.

Review metrics

Metric	Value	Why it matters
Documentation scope	1 line added, 0 removed, 1 file affected	The patch is limited to a third-party integration link and does not alter runtime behavior.

Technical review

Best possible solution:

Keep the external Stream Deck integration discoverable in the established README integration list, backed by CodexBar’s documented loopback service API.

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

Not applicable: this PR changes only README integration discovery text, not a reproducible product behavior.

Is this the best way to solve the issue?

Yes: adding the integration to the existing list matches the nearby third-party integration convention and relies on the documented local service API.

AGENTS.md: found and applied where relevant.

Codex review notes: model internal, reasoning high; reviewed against 453174fe13ee.

Labels

Label changes:

• add P3: This is a low-risk README discovery improvement with no product behavior change.
• add rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🌊 off-meta tidepool and patch quality is 🐚 platinum hermit.
• add status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Not applicable: This is a docs-only PR, so external runtime proof is not required.

Label justifications:

• P3: This is a low-risk README discovery improvement with no product behavior change.
• rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🌊 off-meta tidepool and patch quality is 🐚 platinum hermit.
• status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Not applicable: This is a docs-only PR, so external runtime proof is not required.

Evidence

What I checked:

• Scoped README diff: The branch adds one integration-list entry and changes no runtime code, dependencies, or configuration. (README.md:252, e5d69d8b4b33)
• Supported integration boundary: Current CLI documentation defines codexbar serve as a foreground HTTP server for usage and cost JSON, a dashboard snapshot, and a web UI; the default host is loopback. (docs/cli.md:95, 453174fe13ee)
• Comparable README convention: The adjacent existing entry documents another third-party status-bar integration built on codexbar serve or the bundled CLI. (README.md:251, e5d69d8b4b33)
• Recent API documentation history: Recent current-main history identifies a contributor to the CLI/dashboard documentation surface relevant to external usage displays. (docs/cli.md:95, 5436112ea7b0)

Likely related people:

• Yuxin Qiao: Recent current-main history shows work on the CLI/dashboard documentation surface that defines the external integration contract. (role: recent API documentation contributor; confidence: medium; commits: 5436112ea7b0; files: docs/cli.md, docs/dashboard-api.md)
• Peter Steinberger: The current default-branch tip and latest release documentation update were authored by Peter; the available README history does not expose an earlier owner for the integrations list. (role: recent repository documentation contributor; confidence: low; commits: 453174fe13ee, 5a2a70458d95; files: README.md)

Rating scale

Score	Internal tier	Crab rank	Meaning
6/6	S	🦀 challenger crab	Exceptional readiness
5/6	A	🦞 diamond lobster	Very strong readiness
4/6	B	🐚 platinum hermit	Good normal PR; ordinary maintainer review
3/6	C	🦐 gold shrimp	Useful, but confidence is limited
2/6	D	🦪 silver shellfish	Proof or implementation needs work
1/6	F	🧂 unranked krab	Not merge-ready
N/A	NA	🌊 off-meta tidepool	Rating does not apply

Overall follows the weaker of proof and patch quality.
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.

Workflow

• 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.