Borrowing it
Nothing to install: this file belongs to samuelhe52/AniShelf. 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/samuelhe52/AniShelf/main/.codex/skills/anishelf-release/SKILL.mdgit clone --depth 1 https://github.com/samuelhe52/AniShelfWrote 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/samuelhe52/anishelf/anishelf-release)<a href="https://agentmods.dev/skills/samuelhe52/anishelf/anishelf-release"><img src="https://agentmods.dev/badge/skills/samuelhe52/anishelf/anishelf-release/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/samuelhe52/anishelf/anishelf-release"><img src="https://agentmods.dev/badge/skills/samuelhe52/anishelf/anishelf-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.01507 |
| Opus 5 | $0.00029 | $0.00754 |
| Sonnet 5 | $0.00012 | $0.00301 |
| Haiku 4.5 | $0.00006 | $0.00151 |
Grade A, and why
anishelf-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 2d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AniShelf release
Use this skill for AniShelf's source-control release workflow. Read the repository's AGENTS.md for project conventions and validation constraints. Resolve the paths below from the repository root.
The scope deliberately ends with the merged release branch and published Git tag. Xcode archive/upload, TestFlight rollout, App Store Connect submission, and other app-distribution procedures are handled by the maintainer outside this skill. Do not treat their absence as a release-workflow defect or claim that Git publication means the app has shipped.
For a readiness check or workflow explanation, inspect and report only. For a release-preparation request, complete the requested local preparation and validation before presenting the next approval gate. Resume from verified current state without repeating completed steps. Preserve unrelated working-tree changes throughout.
Prepare and validate
- Inspect the working tree, branch state, and existing release tags. Start release work from an up-to-date
mainand review all changes since the latest applicable release tag. Confirm the intended version and tag before changing version metadata. - Prepare the release metadata together:
- Update the app version in
MyAnimeList.xcodeproj/project.pbxproj; check bothMARKETING_VERSIONandCURRENT_PROJECT_VERSIONfor the app's build configurations. Do not assume the build number should carry forward or change unrelated test-target versions. - Confirm an appropriate entry for the target version in
MyAnimeList/Sources/Models/WhatsNewModels.swift. - Update affected translations in
MyAnimeList/Resources/Localizable.xcstringsand check the localization catalogs for missing translations. String catalogs are JSON;jq emptychecks syntax, not translation completeness.
- Update the app version in
- Check whether
README.md,README.zh-CN.md, anddocs/anishelf_overview.mdneed release-related changes. Update these documents only with explicit user permission. - Use the Makefile for formatting, linting, relevant tests, and a Release build:
make format,make lint, andmake build CONFIGURATION=Release. Review formatting changes to keep unrelated edits out of the release. - Run the smallest relevant tests first, using
APP_TEST_ONLYorDATAPROVIDER_TEST_FILTERas documented inAGENTS.md. Usemake test-simwhen broad validation is warranted andmake run-simfor runtime or UI validation. Reuse an already booted simulator; obtain explicit permission before booting one or performing physical-device validation. - Review the resulting diff and run
git diff --check. Report the checks actually completed and any remaining validation gaps before committing.
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.
- 2d ago Changed · +12 lines e44d25f181f2
- 4d ago First seen · 47 lines · 58 tokens per session scan A d0a3250c79c5
anishelf-release is a skill published in the GitHub repository samuelhe52/AniShelf (133 stars, last pushed 2d ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,507 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 2026-09-06.
Other skills, from other repositories
ios-bump-version
An iOS release helper for changing an app's marketing version, the version number shown to users, and committing the change on the appropriate branch. It first checks the version format, Git state, branch, and current version.
git-branching-workflow
Standardized Git branch creation, naming taxonomies (feat/, fix/, refactor/, hotfix/, release/, chore/), trunk-based integration, and PR isolation lifecycles. Use when creating branches, preparing pull requests, or standardizing team git workflows; do not use for resolving merge conflicts or low-level git plumbing.
plan
Epic decomposition into trackable, right-sized tasks. Three modes — audit-aware (codebase-audit reports), workflow-audit-aware (handoff.yaml with pre-rated findings), standalone (from scratch). Light convention scanning for projects without CLAUDE.md.
workflow-audit
Systematic UI workflow auditing for SwiftUI applications. Discovers entry points, traces user flows, detects dead ends and broken promises, audits data wiring, evaluates from user perspective. Triggers: "workflow audit", "audit flows", "find dead ends", "check navigation".
swift-expert
Expert-level Swift development for iOS, macOS with SwiftUI, Combine, and modern Swift 5.9+. Use when the user mentions iOS, macOS, SwiftUI, Combine, async await, or Apple platforms, or when the task involves Modern Swift Features, Basics and Optionals, Functions and Closures, or Structs and Classes.
swift-architecture-skill
Swift iOS architecture guidance and playbooks for MVVM, MVI, TCA, Clean Architecture, VIPER, MVP, Coordinator, and Reactive patterns. Use when designing, implementing, refactoring, or reviewing the architecture of a SwiftUI or UIKit feature, module, or codebase.