config

config is a skill for Claude Code from swt-labs/vibe-better-with-claude-code-vbw. It costs 37 tokens per session (797 once invoked), scanned A, original, MIT.

A settings command for VBW, including which AI model handles each role, how much work VBW does on its own, and whether its status line is shown. An AI model is the software that produces VBW’s suggestions and code.

In plain words
What is it for?
Use it to view or change model profiles, choose models for individual roles, control effort, and manage the status line.
Why use it?
It lets you adjust the balance between output quality, cost, and automatic activity instead of using only the defaults.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the vbw plugin — 34 skills, 7 agents, 4 hooks shipped together

Good fit Use it to view or change model profiles, choose models for individual roles, control effort, and manage the status line.

Compare 6 skills from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add swt-labs/vibe-better-with-claude-code-vbw
Claude Code
/plugin install vbw

Made for: Claude Code.

Or install vbw, the plugin that ships this one along with the rest of its 34 skills, 7 agents, 4 hooks.

Wrote 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.

agentmods badge for config

README.md
[![agentmods](https://agentmods.dev/badge/skills/swt-labs/vibe-better-with-claude-code-vbw/config/github.svg)](https://agentmods.dev/skills/swt-labs/vibe-better-with-claude-code-vbw/config)
Your own site
<a href="https://agentmods.dev/skills/swt-labs/vibe-better-with-claude-code-vbw/config"><img src="https://agentmods.dev/badge/skills/swt-labs/vibe-better-with-claude-code-vbw/config/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.

agentmods 80×15 button for config

Your own site · 80×15
<a href="https://agentmods.dev/skills/swt-labs/vibe-better-with-claude-code-vbw/config"><img src="https://agentmods.dev/badge/skills/swt-labs/vibe-better-with-claude-code-vbw/config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 797 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.00797
Opus 5.5 $0.00015 $0.00319
Sonnet 5.5 $0.00007 $0.00159
Haiku 4.5 $0.00004 $0.00080

Measured today against content hash 7b195f9330b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

config 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.

plugin/skills/config/SKILL.md · 34 lines

What it actually says

"${CLAUDE_PLUGIN_ROOT}/bin/vbw" config 2>&1 || true
"${CLAUDE_PLUGIN_ROOT}/bin/vbw" statusline status 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).

The user said: $ARGUMENTS

Output above says not a VBW project: set up first (vbw init and vbw statusline on, one line saying so), then run vbw config again.

Change asked: make it with vbw config set KEY VALUE, show the result. Else show the settings above in plain words. Keys:

  • profile: models VBW's agents run on. quality (Opus for Architect, Lead, Dev and Debugger; Sonnet for QA, Scout and Docs), balanced (default: Opus for Architect and Lead, Sonnet for the rest), budget (Haiku for Scout, Sonnet for the rest, QA included).
  • model.<role> (architect, lead, dev, qa, scout, debugger, docs): override one agent (opus, sonnet, haiku, a model id; default removes it). QA never runs on Haiku, only on Sonnet or stronger (it judges whether work meets the spec): model.qa accepts sonnet, opus, default and non-Haiku model ids, and refuses any Haiku id. A stored Haiku value is raised to Sonnet.
  • autonomy: how much /vbw:vibe does alone: guided (explains each step, waits), balanced (default: stops for decisions, approval, checking, shipping), hands-off (takes its own recommendations, lists them).
  • autonomy_cap: steps one autonomous run takes before stopping.
  • rigor: how thorough each phase's checking is. auto (default) picks a tier per phase from its risk; express, standard or deep forces it. Set with vbw config rigor MODE; phases not yet started are re-tiered.
  • motion: panel animation, full, calm or off; default: by interview level.
  • check_jobs: how many checks run at the same time, shared by every VBW command in this project, 1 to 64; default: three quarters of the processor cores (at least 1). Kept in this clone, not in the record. The computer-wide limit (three quarters of the cores, shared by every VBW project, not a setting; docs/proof.md) caps it.
  • command_timeout: seconds vbw prove lets one project command (the test command above all) run before stopping it, 1 to 86400; default: 3600 (60 minutes). A check keeps its own timeout.
  • check_budget: seconds one unit of a proof (a check, project command or test file) may take before the summaries name it over budget, 1 to 86400; default: 120. Reported only, never a limit.
  • Status line: vbw statusline on or off.

Your own session keeps the model you chose with /model; it must be Sonnet, Opus or Fable for auto mode.

Changes

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.

  1. today First seen · 34 lines · 37 tokens per session scan A 7b195f9330b7

Subscribe to this mod's changes

config 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 37 tokens to every session and 797 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.