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/suggest)<a href="https://agentmods.dev/skills/swt-labs/vibe-better-with-claude-code-vbw/suggest"><img src="https://agentmods.dev/badge/skills/swt-labs/vibe-better-with-claude-code-vbw/suggest/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/suggest"><img src="https://agentmods.dev/badge/skills/swt-labs/vibe-better-with-claude-code-vbw/suggest.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 | $0.00035 | $0.00455 |
| Opus 5.5 | $0.00014 | $0.00182 |
| Sonnet 5.5 | $0.00007 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
suggest scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Suggest
"${CLAUDE_PLUGIN_ROOT}/bin/vbw" interview 2>&1 || true
"${CLAUDE_PLUGIN_ROOT}/bin/vbw" suggest list 2>&1 || true
Above: the user's answers (level, explanation depth, involvement) and the suggestions already declined in this project.
When
Only at spec proposal (with the proposed requirements) and at plan approval (with the plan). Never offer or ask mid-run, mid-build, during a run, or while a step is working; the user is not interrupted for ideas.
What
At most three suggestions, each one yes or no. None is required: zero is valid, and when nothing worth raising exists, say nothing about suggestions. Never pad to reach three.
Match them to the user's level and explanation depth: for a first-time builder, plain outcomes ("Should visitors be able to find the page by searching?"); for a senior engineer, terse technical ones (rate limiting, migrations, observability). With no interview answers, stay neutral: plain and brief.
Before offering, read vbw show requirements and vbw show decisions. Never
offer a duplicate of a requirement or a decision, and never offer one whose text
matches the declined list above.
Answers
Ask with AskUserQuestion, one question per suggestion: "Yes", "No". The user may decline any.
- Yes, a testable outcome:
vbw spec add auto|human "statement"(as the router does for any requirement). - Yes, a choice or constraint:
vbw decide "<what>" "<why: accepted on suggestion>". - No:
vbw suggest decline "<the suggestion's exact text>". A declined suggestion is never offered again in this project; never offer it again, reworded or not.
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 · 35 tokens per session scan A c6d319178fa9
suggest 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 35 tokens to every session and 455 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,"…