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 commands/alberduris/skills/releasegit clone --depth 1 https://github.com/alberduris/skillsWrote 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/commands/alberduris/skills/release)<a href="https://agentmods.dev/commands/alberduris/skills/release"><img src="https://agentmods.dev/badge/commands/alberduris/skills/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 | $0.00000 | $0.00975 |
| Opus 5 | $0.00000 | $0.00487 |
| Sonnet 5 | $0.00000 | $0.00195 |
| Haiku 4.5 | $0.00000 | $0.00097 |
Grade A, and why
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 4d 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.
What it actually says
Release Procedure
Skills marketplace release. Version tracked per skill.
[!IMPORTANT]: BEFORE ANY RELEASE, CREATE A CHECKLIST WITH TodoWrite.
Do NOT release from memory. Create tasks for each step and mark them complete as you go.
Release Checklist (copy to TodoWrite):
1. All changes committed with conventional prefixes (see Commit Conventions)
2. Version bumped in ALL version files that exist for this skill (see Version Files)
3. If skill has a build system, build and test pass
4. git push origin main
[!SKILL-STRUCTURE]: For npx skills add discovery, every skill MUST have this directory layout: a) plugins/<skill>/.claude-plugin/plugin.json (name, version, description, author), b) plugins/<skill>/skills/<skill>/SKILL.md (frontmatter + directives). Commands, templates, scripts, and references live under plugins/<skill>/skills/<skill>/. Without both plugin.json and the nested skills/<skill>/ path, the installer will NOT find the skill.
[!VERSION-FILES]: Three version files are guaranteed across all skills. Additional version files may exist depending on the skill's internal structure (e.g. package.json, Cargo.toml, setup.py). All that exist MUST match.
version_files:
# Always present:
- file: SKILL.md
path: plugins/<skill>/skills/<skill>/SKILL.md
field: frontmatter → version
read_by: Agent (skill loader)
- file: plugin.json
path: plugins/<skill>/.claude-plugin/plugin.json
field: version
read_by: Skill installer (npx skills add)
- file: marketplace.json
path: .claude-plugin/marketplace.json
field: plugins[name=<skill>].version
read_by: Marketplace registry
# Skill-specific (check if they exist):
# Any file that declares a version (package.json, Cargo.toml, pyproject.toml, etc.)
# must be kept in sync with the above.
[!VERSION-SYNC-RULE]: If any version files diverge, align them all before releasing.
[!VERSION-BUMP]: Before each release, REASON about what bump is appropriate:
- Run
git log <last-tag>..HEAD --onelineto see all changes since last release - Apply the commit convention rules to determine the bump
- Semver: patch (0.0.X), minor (0.X.0), major (X.0.0)
[!COMMIT-CONVENTIONS]: Use conventional prefixes scoped to the skill:
prefixes:
- prefix: "fix(<skill>):"
meaning: Bug fix
bump: patch
- prefix: "feat(<skill>):"
meaning: New feature
bump: minor
- prefix: "breaking(<skill>):"
meaning: Breaking change
bump: major
- prefix: "refactor(<skill>):"
meaning: Code restructuring, no behavior change
bump: patch
- prefix: "docs(<skill>):"
meaning: Documentation only
bump: patch
- prefix: "chore(<skill>):"
meaning: Build, tooling, maintenance
bump: patch
Commit message format: <prefix>(<skill>): <description>, bump to <version>
The highest-priority prefix in the log determines the bump:
- Any
breaking:in the log -> major - Any
feat:-> minor - Only
fix:/refactor:/docs:/chore:-> patch
[!RELEASE-PROCEDURE]: To release a new version of a skill:
-
Make changes in
plugins/<skill>/ -
Bump version in all version files that exist for this skill (see Version Files)
-
If the skill has a build system (package.json, Makefile, Cargo.toml, setup.py, etc.), run the build and tests.
-
Stage files
git add .claude-plugin/marketplace.json plugins/<skill>/...If the skill produces build artifacts that are gitignored, use
git add -fto include them. -
Commit with conventional prefix
git commit -m "<prefix>(<skill>): <description>, bump to X.Y.Z" -
Push
git push origin main
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.
- 4d ago First seen · 114 lines · 0 tokens per session scan A aea66e68c359
release is a command published in the GitHub repository alberduris/skills (18 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 975 tokens. 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 commands, from other repositories
changelog
Generate a new changelog entry by reading all changeset files and creating a properly formatted entry in .changelog/v3.mdx.
ship
Archive completed feature with lessons learned (Phase 4).
merge-and-status
Merge the current PR, pull main, surface any open contributor PRs and untriaged contributor issues, and show open milestone issues.
ship
Deliver the increment. Then go live with a rollback you have run.
update-changelog-and-tag
You are preparing a release. Follow these steps precisely.
release-tag
Create and push a version tag after a release PR has been merged.