decant: Skill for Claude Code

.claude/skills/decant-release/SKILL.md

decant-release is a skill for Claude Code from dosu-ai/decant. It costs 60 tokens per session (444 once invoked), scanned A, original, Apache-2.0.

A release procedure for publishing a new signed Decant version. It creates a version tag that starts automated publishing to GitHub Releases, npm, a container registry, and the Homebrew package repository.

In plain words
What is it for?
Use it to check whether Decant is ready for release or to tag and publish an approved version.
Why use it?
Publishing cannot easily be undone, so the procedure checks the branch, tests, continuous integration, signing, and explicit approval before pushing anything. It reduces the risk of releasing from the wrong commit or version.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is dosu-ai/decant's own configuration. It tells Claude Code how to work on decant itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything decant configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dosu-ai/decant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dosu-ai/decant/main/.claude/skills/decant-release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dosu-ai/decant

Made for: Claude Code.

Wrote 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.

agentmods badge for decant-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/dosu-ai/decant/decant-release/github.svg)](https://agentmods.dev/skills/dosu-ai/decant/decant-release)
Your own site
<a href="https://agentmods.dev/skills/dosu-ai/decant/decant-release"><img src="https://agentmods.dev/badge/skills/dosu-ai/decant/decant-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.

agentmods 80×15 button for decant-release

Your own site · 80×15
<a href="https://agentmods.dev/skills/dosu-ai/decant/decant-release"><img src="https://agentmods.dev/badge/skills/dosu-ai/decant/decant-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 444 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.00444
Opus 5.5 $0.00024 $0.00178
Sonnet 5.5 $0.00012 $0.00089
Haiku 4.5 $0.00006 $0.00044

Measured 28d ago against content hash 1acd64c8bd7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

decant-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 28d 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.

.claude/skills/decant-release/SKILL.md · 45 lines

What it actually says

Release Decant

Publishing is irreversible: npm versions cannot be reused and the Homebrew tap updates for every user.

Stop and ask the user for explicit approval before running just release, pushing any tag, dispatching release.yml, merging with --admin, or re-running a release job. An earlier approval in the same conversation does not cover a new tag.

Preflight

  1. On main, clean tree, up to date with origin/main.
  2. just check passes locally (needs network for the npm pack smoke).
  3. CI is green on the exact commit you will tag.
  4. Pick the version: semver without a leading v. Prerelease suffixes such as -beta.1 and backport tags below the newest release publish to narrower channels; docs/distribution.md describes which.

Tag

just release VERSION re-checks step 1 of the preflight only, then creates a signed annotated tag vVERSION and pushes it, so the approval above must come first. Signing is required; do not bypass it.

What the tag triggers

.github/workflows/release.yml builds the platform binaries (codesigned when signing secrets are configured), attests them, publishes GitHub Release assets with SHA256SUMS, publishes the npm launcher and platform packages with provenance, pushes the GHCR image, and updates the formula in dosu-ai/homebrew-dosu.

Afterwards

Follow "Verify a release" in docs/distribution.md (checksums, gh attestation verify, npm audit signatures) and report the results. If a job fails, report the failing step and wait for the user before re-running or retagging.

Changes

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.

  1. 28d ago First seen · 45 lines · 60 tokens per session scan A 1acd64c8bd7a

Subscribe to this mod's changes

decant-release is a skill published in the GitHub repository dosu-ai/decant (72 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 444 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-30.

Related

Other skills, from other repositories

ci-cd-pipeline-authoring

Use when a repository needs CI/CD - author GitHub Actions workflows so TaskTrooper's pipeline auto-detects your validate/build/test jobs and stage/preprod/prod deploys, and so a dispatch delivery profile can dispatch the production deploy.

makifbaysal/tasktrooper · 56 tokens

aiox-devops

Activate Gage (devops) for GitHub Repository Manager & DevOps Specialist. Use for repository operations, version management, CI/CD, quality gates, and GitHub push operations. ONLY agent authorized to push to remote repository.

SynkraAI/aiox-core · 51 tokens

aiox-devops

GitHub Repository Manager & DevOps Specialist (Gage). Use for repository operations, version management, CI/CD, quality gates, and GitHub push operations. ONLY agent authorized...

SynkraAI/aiox-core · 41 tokens

wicked-garden-platform-gh-cli

Use when you need gh CLI patterns beyond the basics — debugging failed workflow runs, bulk PR operations, release automation, or repo health checks. Provides composable gh invocations for power users. NOT for simple git commands (use Bash) or GitLab (use the glab-cli skill). Use when: "debug the failed workflow run"…

mikeparcewski/wicked-garden · 117 tokens

hatch3r-release

Cuts a release with version bump, changelog, tagging, and deploy verification. Use when preparing a release, cutting a version, or deploying to production.

hatch3r/hatch3r · 37 tokens

wicked-garden-platform-glab-cli

Use when you need glab CLI patterns for GitLab — pipeline debugging, MR management, or release automation. Provides composable glab invocations for power users. NOT for GitHub (use the gh-cli skill) or simple git commands (use Bash).

mikeparcewski/wicked-garden · 62 tokens