Borrowing it
Nothing to install: this file belongs to swt-labs/vibe-better-with-claude-code-vbw. 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/swt-labs/vibe-better-with-claude-code-vbw/main/.claude/skills/vbw-release/SKILL.mdgit clone --depth 1 https://github.com/swt-labs/vibe-better-with-claude-code-vbwWrote 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/swt-labs/vibe-better-with-claude-code-vbw/vbw-release)<a href="https://agentmods.dev/skills/swt-labs/vibe-better-with-claude-code-vbw/vbw-release"><img src="https://agentmods.dev/badge/skills/swt-labs/vibe-better-with-claude-code-vbw/vbw-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/swt-labs/vibe-better-with-claude-code-vbw/vbw-release"><img src="https://agentmods.dev/badge/skills/swt-labs/vibe-better-with-claude-code-vbw/vbw-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 | $0.00038 | $0.00739 |
| Opus 5.5 | $0.00015 | $0.00296 |
| Sonnet 5.5 | $0.00008 | $0.00148 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
vbw-release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Releasing VBW
Every step runs; a failure stops the release until its root cause is fixed.
- Tests:
PATH="/bin:$PATH" /bin/bash tools/test.sh --releaseonce, under macOS/bin/bash3.2 (the floor); it uses half the cores. This is the release run: the proof's run plus the timed speed checks (both benchmarks and the timed files), which are judged here and nowhere else, so they must be within budget. Linux bash 5 and macOS bash 3.2 run again in CI after the push, as information: the owner updates once this run passed; a Linux failure that cannot affect macOS waits for the batch before 2.1.0 (D402).tools/test-linux.shstays for chasing a Linux-only failure. When the last proof passed (results it reused count: the read lists still vouch for them), left no command skipped and no quick command standing in, and only the version files andplugin/CHANGELOG.mdchanged since, the run reuses it: it runs only the benchmarks and the timed files, and prints the proof's time. Any other change, or no such proof, runs everything and says why. - Real-user scenarios:
bash tools/l3-suite.sh SCENARIO...(the real Claude Code TUI, driven as a user; each scenario costs API credits). Run only the scenarios of the area the release changed, plusgreenfieldwhen the release touches the core loop (the router,vbw next, a workflow, the proof or QA). The full suite runs before the 2.1 launch. The release record names the scenarios run and those not run. Every check must pass. - Version:
bash tools/bump-version.sh --set X.Y.Z(all five version files), then aplugin/CHANGELOG.mdentry written for users: what they can do now, what was fixed, anything they must do. Every build a user is meant to receive gets a new version: Claude Code updates a plugin only when its version changes. - Claude Code changes: read the Claude Code changelog for every version since the last release and check what touches plugins, hooks, mods, skills, the status line or settings (a maintainer step, never part of VBW).
- Docs:
README.mdanddocs/match what was built (commands, settings, requirements). - Publish, only on the owner's word: push the branch. CI (macOS bash 3.2, Linux bash 5, manifest validation) reports afterwards: a macOS or manifest failure is fixed at once; a Linux-only one goes to the batch before 2.1.0.
- Verify the update path: in a throwaway
CLAUDE_CONFIG_DIR, install the previous release, then update withclaude plugin marketplace updateandclaude plugin update; the new version must be installed and load. - Record the release in the progress log with its evidence levels and a Not tested list.
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.
- today First seen · 45 lines · 38 tokens per session scan A ed6acc5b03e0
vbw-release is a skill published in the GitHub repository swt-labs/vibe-better-with-claude-code-vbw (85 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 739 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 2026-10-22.
Other skills, from other repositories
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
validate-release-green
Run or inspect the local Release-Green observer for an exact base or combined PR candidate, separating hard failures, advisory drift and incomplete evidence. Use for maintainer preflight; full CI acceptance remains a separate requirement.
verify-and-ship
Choose proportionate validation, fix failures, update the changelog, commit, push, and create/update the pull request or merge request.
ship
Pre-release gate — run the full gate, responsive + render checks, then produce the release checklist (README badge/current/changelog). Use before tagging a release.
ship-workflow
Resumable shipping lifecycle: reconciles current Git and GitHub facts from any entry (dirty default or feature branch, local commits, published branch, open PR, existing manual or native stack, merged work), commits dirty work as lossless logical commits, publishes or reuses the PR, requires current CI and review…
AI Release Guardian
Analyze a git diff, map affected risks, select the tests that matter, detect coverage gaps on changed lines, run configurable quality gates, and produce a go/no-go release report with cited evidence. Recommends only; never merges or deploys.