Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Data-Wise/craftnpx agentmods add skills/data-wise/craft/releaseWrote 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/data-wise/craft/release)<a href="https://agentmods.dev/skills/data-wise/craft/release"><img src="https://agentmods.dev/badge/skills/data-wise/craft/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/data-wise/craft/release"><img src="https://agentmods.dev/badge/skills/data-wise/craft/release.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00070 | $0.03878 |
| Opus 5.5 | $0.00028 | $0.01551 |
| Sonnet 5.5 | $0.00014 | $0.00776 |
| Haiku 4.5 | $0.00007 | $0.00388 |
Grade A, and why
release 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://data-wise.github.io/craft/ | grep -o 'version-[0-9]\+\.[0-9]\+\.[0-9]\+' | head -1 | sed 's/^version-/v/' How it starts
The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Pipeline
Orchestrate end-to-end releases with pre-flight validation, version bumping, PR creation, merge, and GitHub release — all in one flow.
When to Use
- User says "release", "ship it", "cut a release", or similar
- User wants to publish a new version to GitHub/npm/PyPI
- User is ready to merge dev to main and tag a release
Prerequisites
- Must be on
devbranch (or have dev up to date) - All feature work merged to dev via PRs
- Working tree clean (no uncommitted changes)
Arguments
| Argument | Alias | Description | Default |
|---|---|---|---|
--dry-run |
-n |
Preview release plan without executing | false |
--autonomous |
--auto |
Run without user prompts, auto-resolve where possible | false |
--skip-surfaces |
— | Skip Step 13.6 surface registry phase (propagation + verify) | false |
Dry-Run Mode
When --dry-run or -n is passed, execute only Step 1 (version detection), then display a preview of every remaining step and exit. No mutations occur.
Risk Level: HIGH (modifies git history, creates PRs, publishes releases)
Dry-Run Output
After detecting the current and next version, display:
┌─────────────────────────────────────────────────────────────┐
│ /release --dry-run │
├─────────────────────────────────────────────────────────────┤
│ Current version: v2.17.0 │
│ Next version: v2.18.0 (minor — feat: commits detected) │
├─────────────────────────────────────────────────────────────┤
│ Actions that WOULD be taken: │
│ │
│ 1. ✓ /craft:check --for release (full CI mirror) │
│ 2. ✓ Run pre-release-check.sh v2.18.0 (metadata) │
│ 3. ✓ Bump version in plugin.json, CLAUDE.md │
│ 3b. ✓ /craft:docs:update --post-merge (semantic doc sync) │
│ 3b.5 ✓ docs-staleness-check.sh --non-interactive (gate) │
│ 4. ✓ Commit: "chore: bump version to v2.18.0 for release" │
│ 5. ✓ Push to dev │
│ 6. ✓ Create PR: dev → main │
│ 6.5 ✓ CI monitoring (poll → diagnose → fix → retry) │
│ 7. ✓ Merge PR (--merge, NO --delete-branch) │
│ 8. ✓ Create GitHub release v2.18.0 on main │
│ 9. ✓ mkdocs build --strict && mkdocs gh-deploy │
│ 10. ✓ Update Homebrew tap (formula or cask) │
│ (10b if Tauri: build → upload → SHA256 → cask → tap) │
│ (10b verify_caveats.py — advisory caveats gate) │
│ (10c post_install_check.py — advisory structural gate) │
│ (10d aggregator-sync.yml CI action — BLOCKING on unmerged PR) │
│ 11. ✓ Sync dev with main │
│ 12. ✓ Verify CI on main │
│ 13. ✓ Verify downstream (docs, brew, badges, cask) │
│ 13.5 ✓ Post-release sweep (Tier 2+ drift detection) │
├─────────────────────────────────────────────────────────────┤
│ ⚠ Risk: HIGH — modifies git history, creates PRs │
│ ⚠ No changes were made. Run without --dry-run to execute. │
└─────────────────────────────────────────────────────────────┘
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 354 lines · 70 tokens per session scan A 7aa5c099955d
release is a skill published in the GitHub repository Data-Wise/craft (4 stars, last pushed 9d ago), licensed MIT. It adds 70 tokens to every session and 3,878 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
swarm-migrate
Cross-repo migration swarm — one coordinator + N parallel subagents (one per target repo) that apply the same transformation, open PRs, wait for CI, and report back to a shared JSON ledger. Coordinator handles topology, conflict auto-rebase, and stop-on-novel-failure. Use when bumping a shared dependency, rolling out…
pdlc-ship
A software release workflow that runs tests, updates the version and change log, creates a Git tag, and starts CI/CD, the automated build and deployment process.
tfx-ship
A release workflow for publishing triflux versions through GitHub Releases, the npm package registry, and the Claude Code marketplace. It also supports version changes, dry runs, skipped tests, and no-publish runs.
xberg-release
Xberg release on top of the shared release-workflow: task version:sync to bindings and chart, CI/Publish/Benchmarks readiness. Use before a release.
gitlab-devops
GitLab DevOps operations — issues, merge requests, CI/CD pipelines, repository browsing, labels, milestones, releases, and wiki management. Use when querying GitLab project status, monitoring pipeline executions, browsing repository files, creating issues for network findings, opening merge requests for config…
seed-snapshot-release
An automated workflow for creating and tracking a snapshot release of the pull request on the current branch. A snapshot release is a temporary package build used for testing a branch before a normal release.