Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add swt-labs/vibe-better-with-claude-code-vbw/plugin install 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/help)<a href="https://agentmods.dev/skills/swt-labs/vibe-better-with-claude-code-vbw/help"><img src="https://agentmods.dev/badge/skills/swt-labs/vibe-better-with-claude-code-vbw/help/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/help"><img src="https://agentmods.dev/badge/skills/swt-labs/vibe-better-with-claude-code-vbw/help.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 | $0.00018 | $0.00701 |
| Opus 5.5 | $0.00007 | $0.00280 |
| Sonnet 5.5 | $0.00004 | $0.00140 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
help scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
"${CLAUDE_PLUGIN_ROOT}/bin/vbw" interview 2>&1 || true
Write to the user's level, explanation depth and involvement (above; "-": plain words).
Show the user this, as is:
VBW turns what you want into proven, committed work. You agree on requirements and decide; VBW plans them with tests, you approve, VBW builds in parallel and proves each requirement, you check what only a person can judge, and you ship.
| Command | What it does |
|---|---|
| Everyday | |
/vbw:vibe [what you want] |
The one command: takes the project to its next step, stops when it needs you |
/vbw:approve |
Approve the plan, its tests and the commands it may run (only you can); VBW also offers it as a choice where Enter approves |
/vbw:status |
Where the project stands |
| Think and decide | |
/vbw:discuss [topic] |
Think something through; the outcome is recorded |
/vbw:research [question] |
A sourced answer with a recommendation |
/vbw:todo [idea], /vbw:list-todos |
Park an idea for later; see the list |
| Check the work | |
/vbw:qa |
Run every proof now and explain the result |
/vbw:verify |
Check, one at a time, what only you can judge |
/vbw:debug [the problem] |
Find a bug's root cause |
/vbw:fix [what] |
A quick fix without planning; proofs re-run after |
| Your project | |
/vbw:init |
Set up VBW and its status line |
/vbw:convert |
Bring a VBW 1 project into VBW 2 |
/vbw:map |
Map an existing codebase |
/vbw:teach [convention] |
Teach VBW your project's conventions |
/vbw:pause, /vbw:resume |
Stop safely; pick up where you left off |
| Settings and tools | |
/vbw:profile [careful/standard/fast] |
Models, autonomy and how VBW talks to you, in one switch |
/vbw:config |
Each setting on its own |
/vbw:skills, /vbw:rtk, /vbw:compress |
Community skills; token-saving compression |
/vbw:doctor |
Check VBW's setup |
/vbw:panel |
Whether the panel and its "needs you" sound work here; /vbw-panel and /vbw-sound use them |
/vbw:report |
Prepare a bug report (you see it first) |
/vbw:update, /vbw:whats-new, /vbw:uninstall |
Update VBW, see what changed, remove it |
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 · 50 lines · 18 tokens per session scan A 307defd3a240
help 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 18 tokens to every session and 701 once invoked, about $0.0001 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
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…