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/qa)<a href="https://agentmods.dev/skills/swt-labs/vibe-better-with-claude-code-vbw/qa"><img src="https://agentmods.dev/badge/skills/swt-labs/vibe-better-with-claude-code-vbw/qa/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/qa"><img src="https://agentmods.dev/badge/skills/swt-labs/vibe-better-with-claude-code-vbw/qa.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 | $0.00028 | $0.00430 |
| Opus 5.5 | $0.00011 | $0.00172 |
| Sonnet 5.5 | $0.00006 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
qa scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
"${CLAUDE_PLUGIN_ROOT}/bin/vbw" show requirements 2>&1 || true
"${CLAUDE_PLUGIN_ROOT}/bin/vbw" show qa 2>&1 || true
"${CLAUDE_PLUGIN_ROOT}/bin/vbw" interview 2>&1 || true
Write to the user's level, explanation depth and involvement (above; "-": plain words).
- If the contract is approved, run
vbw prove --full; otherwise say the plan and its tests wait for approval, ask only with the approval menu (AskUserQuestion), never to type a command, and stop. - Explain the result in plain words, requirement by requirement: proven,
failing (with the reason from
vbw show evidence), or still being built. Name any failed project command, any commit that changed files outside its plan, and any file a plan delivered that was changed or deleted outside any plan (delivered:lines ofvbw show evidence; QA cannot pass its phase until a fix brings it back or the user decides to keep the change). - The
[human]requirements no check can prove: list the ones whose work is built (builtabove) and offer/vbw:verifyto check them now. - From
vbw show qa(above), tell the user which phases are checked again and why, and which phases keep their pass (their earlier pass still stands), in plain words at their level, explanation depth and involvement. Say it before the results, and explain any term a beginner would not know. - If something fails, say what happens next:
/vbw:vibefixes failures (each becomes a fix item, worked and proved again).
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 · 32 lines · 28 tokens per session scan A a1ac2094f827
qa 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 28 tokens to every session and 430 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.