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 skills/baijum/ukulele-companion/github-releasenpx skills add baijum/ukulele-companion --skill github-releasegit clone --depth 1 https://github.com/baijum/ukulele-companionWrote 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/baijum/ukulele-companion/github-release)<a href="https://agentmods.dev/skills/baijum/ukulele-companion/github-release"><img src="https://agentmods.dev/badge/skills/baijum/ukulele-companion/github-release.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 5.1 | $0.00053 | $0.00708 |
| Opus 5 | $0.00026 | $0.00354 |
| Sonnet 5 | $0.00011 | $0.00142 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
github-release 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 5d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Release
For normal releases, use
/releaseinstead — it creates the tag, bumps both platform versions, builds, and uploads in one workflow. This skill is for creating a tag without building.
Create a version tag on main and a GitHub release with release notes summarizing changes since the previous tag.
Prerequisites
ghCLI authenticated (gh auth status)- Working tree is clean (
git statusshows no uncommitted changes) - You are on the
mainbranch and up to date with origin
Workflow
Step 1: Verify clean state
git status
git branch --show-current
Confirm the branch is main and there are no uncommitted changes. If the working tree is dirty, stop and ask the user to commit or stash first.
Step 2: Determine the next version
Read the latest existing tag:
git describe --tags --abbrev=0
The project uses semantic versioning (major.minor.patch) with a v prefix (e.g., v9.10.1).
If the user did not specify a version or release type, ask which type of release to create:
| Release type | What changes | Example |
|---|---|---|
| Major | Bump major, reset minor and patch to 0 | 9.10.1 -> 10.0.0 |
| Feature | Bump minor, reset patch to 0 | 9.10.1 -> 9.11.0 |
| Bugfix | Bump patch | 9.10.1 -> 9.10.2 |
Ask the user to confirm the new version before proceeding.
Step 3: Create and push the tag
Create an annotated tag on HEAD and push it:
git tag -a v<version> -m "v<version>"
git push origin v<version>
Step 4: Generate release notes
Review commits since the previous tag to build the release notes:
git log <previous-tag>..v<version> --oneline
Summarize the changes into categories (Add, Fix, Update, Refactor, etc.) matching the project's commit format.
Step 5: Create GitHub release
Use the gh CLI to create the release. Do not attach any binary files -- binaries are distributed through the Play Store and App Store.
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.
- 5d ago First seen · 90 lines · 53 tokens per session scan A 601fa22c9d31
github-release is a skill published in the GitHub repository baijum/ukulele-companion (13 stars, last pushed 2d ago), licensed MIT. It adds 53 tokens to every session and 708 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
bump-version
Bump la version des specs Redface 2 (footer config.yml + CHANGELOG) et prépare un commit propre. Use when user asks to release a new specs version or prepare v0.X.Y.
radar
Scanne issues, PRs, branches, milestones, CI et roadmap.md de Redface 2 et produit un rapport en 4 buckets (urgent / court terme / roadmap proche / gros chantiers). Spécialisé Redface 2 (lit la phase courante depuis methodology.md, les milestones, les dépendances externes déclarées dans roadmap.md). Mode collecte par…
spec-reality
Vérifie l'alignement entre les specs canoniques (docs/specs/), les ADR (docs/adr/) et le code réel de Redface 2 (settings.gradle.kts, libs.versions.toml, modules Kotlin). Détecte les écarts par sévérité (critique / important / mineur). Complémentaire à spec-check (cross-spec) et spec-audit (audit lourd des specs…
parse-fixture
Analyser une fixture HTML HFR (type de page, sélecteurs CSS, parser cible, variantes logué/non-logué, données sensibles à nettoyer). Use when user provides an HTML file from forum.hardware.fr for parser spec alignment.
spec-audit
Audit exhaustif des specs Redface 2 pour détecter incohérences, lacunes et erreurs factuelles, avec classement par sévérité et fixes proposés. Use when user asks for a specs audit, review, or before bumping to a new version.
codex-review
Fait cadrer/relire/valider un plan, un diff ou un prompt par un agent distinct (Codex) hors-bande, et intègre le verdict. Use for the project's separate-validator cadence (framing before a non-trivial change, diff review, gate before merge).