robinebers/openusage is a native macOS menu-bar application that tracks usage of AI coding subscriptions, including limits, credits, and spending. Developers use it to monitor plans from services such as Claude, Codex, Cursor, and Copilot, while the catalogue entries support related workflows.
Borrowing it
Nothing to install: this file belongs to robinebers/openusage. 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/robinebers/openusage/main/.agents/skills/release-swift/SKILL.mdgit clone --depth 1 https://github.com/robinebers/openusageWrote 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/robinebers/openusage/release-swift)<a href="https://agentmods.dev/skills/robinebers/openusage/release-swift"><img src="https://agentmods.dev/badge/skills/robinebers/openusage/release-swift/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/robinebers/openusage/release-swift"><img src="https://agentmods.dev/badge/skills/robinebers/openusage/release-swift.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 88 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.02047 |
| Opus 5.5 | $0.00000 | $0.00819 |
| Sonnet 5.5 | $0.00000 | $0.00409 |
| Haiku 4.5 | $0.00000 | $0.00205 |
Grade A, and why
release-swift scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://robinebers.github.io/openusage/appcast.xml" | grep -F "OpenUsage-{version}.dmg" How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Swift
Pushing a v* tag on main runs .github/workflows/release.yml, which builds, signs, notarizes, attaches OpenUsage-<version>.dmg to the GitHub Release, and updates the Sparkle appcast.xml on gh-pages. CI creates the release with an EMPTY body, so this skill generates the changelog, records it in CHANGELOG.md, and publishes the notes onto the release.
Channels
- Beta (Early Access): suffixed tag like
v0.7.1-beta.1. Marked a GitHub pre-release and added to Sparkle'sbetachannel. Only users with Early Access enabled get it; GitHub "Latest" is untouched. - Stable: plain tag like
v0.7.1. Marked non-prerelease, becomes GitHub "Latest", and ships to everyone.
The tag IS the version: v0.7.1-beta.1 becomes CFBundleShortVersionString = 0.7.1-beta.1, and CFBundleVersion is the git commit count. There are no version files to bump.
Cutting a release
1. Choose the version
Next number in the current lane (default bump: patch). Beta builds add a -beta.N suffix. Confirm with the owner before proceeding.
2. Generate the changelog
Collect commits since the previous release in the same channel and categorize each:
- Stable cut: span from the last stable tag to this one (e.g.
v0.7.0...v0.7.1), so the notes roll up the entire beta series plus any post-beta commits. Never start a stable changelog at the last beta — that would omit every beta in the lane. - Beta cut: span from the previous tag (the prior beta, or the last stable if it's the first beta in a lane) to this one.
| Commit prefix | Category |
|---|---|
feat, feature, or starts with "Add" |
New Features |
fix or starts with "Fix" |
Bug Fixes |
refactor, enhance |
Refactor |
chore, style, docs, perf, test, ci, build |
Chores |
| Uncategorized | Bug Fixes |
Author attribution (required on every entry):
- With a PR number
(#123):gh pr view 123 --json author -q '.author.login'. - Without a PR number:
gh api /repos/robinebers/openusage/commits/{full_hash} -q '.author.login'. - If the API returns null, fall back to the git author name.
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 Changed · +2 lines 86acdca01eb5
- 2d ago Changed · +7 lines 140303fd7e23
- 8d ago Changed 630bd6638001
- 2mo ago First seen · 142 lines · 0 tokens per session scan A c5c59924c937
release-swift is a skill published in the GitHub repository robinebers/openusage (4,556 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,047 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
release-swift compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| release-swiftrobinebers/openusage | Skill | 4.6k | yesterday | MIT | A | 0 | Claude Code, Codex |
| uploaddrafthq/draft | Skill | 40 | 16d ago | MIT | A | 32 | Claude Code |
| wednesday-gitwednesday-solutions/ai-agent-skills | Skill | 172 | 5mo ago | MIT | A | 35 | Claude Code, Codex |
| fork-and-publish-skillastra-sh/qvr | Skill | 23 | 4mo ago | MIT | A | 139 | Claude Code, Codex |
| git-workflow-and-versioningaddyosmani/agent-skills | Skill | 114k | 5d ago | MIT | A | 131 | Claude Code |
| gentle-ai-collab-perfectGentleman-Programming/gentle-ai | Skill | 8.4k | yesterday | MIT | A | 106 | Claude Code, Codex |
| work-unit-commitsGentleman-Programming/gentle-ai | Skill | 8.4k | yesterday | MIT | A | 33 | Claude Code, Codex |