vibe-better-with-claude-code-vbw: Instructions file for Claude Code

AGENTS.md

vibe-better-with-claude-code-vbw AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from swt-labs/vibe-better-with-claude-code-vbw. It costs 5,343 tokens per session, scanned C, original, MIT.

A set of instructions for VBW, a Claude Code plugin with structured development workflows built around planning, execution, and verification. It also explains how to debug the plugin and locate its logs and private test target.

In plain words
What is it for?
It helps follow VBW's development workflow, check its setup, diagnose incorrect behavior, find Claude Code logs, and configure a local debugging target.
Why use it?
It gives contributors a consistent way to use and troubleshoot the plugin without guessing which local repository or configuration it should use.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: $CLAUDE_PROJECT_DIR variable, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

This is swt-labs/vibe-better-with-claude-code-vbw's own configuration. It tells Claude Code, Codex and OpenCode how to work on vibe-better-with-claude-code-vbw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vibe-better-with-claude-code-vbw configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/swt-labs/vibe-better-with-claude-code-vbw/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/swt-labs/vibe-better-with-claude-code-vbw

Made for: Claude Code, Codex, OpenCode.

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 vibe-better-with-claude-code-vbw AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/swt-labs/vibe-better-with-claude-code-vbw/agents-md.svg)](https://agentmods.dev/instructions/swt-labs/vibe-better-with-claude-code-vbw/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/swt-labs/vibe-better-with-claude-code-vbw/agents-md"><img src="https://agentmods.dev/badge/instructions/swt-labs/vibe-better-with-claude-code-vbw/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,343 This file is loaded in full into every session.
When invoked 5,343 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.05343 $0.05343
Opus 5 $0.02671 $0.02671
Sonnet 5 $0.01069 $0.01069
Haiku 4.5 $0.00534 $0.00534

Measured 8d ago against content hash 4d4229ac27ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

vibe-better-with-claude-code-vbw AGENTS.md scanned grade C with 1 finding 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 8d ago.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Toggle**: Edit `~/.claude-code-router/config.json` and set `CLAUDE_PATH` to one of the above. Optionally `rm -rf "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/commands/vbw"` before relaunching to clear stale command cache.
AGENTS.md · 333 lines

How it starts

The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VBW Instructions

A Claude Code plugin adding structured development workflows (plan → execute → verify) via 7 specialized agent teams. Zero external dependencies beyond jq and git. All logic is bash scripts + markdown.

Communication Style

  • No AI fluff. Skip phrases like "Thanks for the thoughtful feedback!", "Happy to help!", "I appreciate...", etc.
  • No soliciting opinions. Don't end responses with "Would you like me to...", "Let me know if...", "What do you think?", etc.
  • Direct and terse. State facts, provide options when relevant, then stop.

Debugging VBW Behavior

When the user reports VBW misbehavior — pasting Claude Code session output, describing incorrect command behavior, or showing unexpected file state — first resolve the contributor's local debug target repo instead of guessing a maintainer-specific path.

Local debug target configuration (private, not committed)

Preferred setup in the VBW clone's shared Git common dir:

$(git rev-parse --git-common-dir)/info/vbw-debug-target.txt

In a standard non-worktree clone, this usually resolves to:

.git/info/vbw-debug-target.txt

The first non-empty, non-comment line must be the absolute path to the contributor's primary VBW consumer/test repo. Relative paths are rejected so the resolver produces the same result regardless of the caller's current working directory.

Example local file content:

/absolute/path/to/your-test-repo

This file lives under the clone's shared Git metadata, so it stays private and all worktrees created from that clone can read it automatically.

Legacy fallback for a single checkout only:

.claude/vbw-debug-target.txt

That legacy file remains supported and gitignored, but it is scoped to one checkout/worktree and will not be copied into new worktrees.

Resolution order:

  1. VBW_DEBUG_TARGET_REPO env var (one-off override, absolute path only)
  2. $(git rev-parse --git-common-dir)/info/vbw-debug-target.txt in the current clone (preferred persistent local config, shared across worktrees)
  3. ./.claude/vbw-debug-target.txt in the current checkout/worktree (legacy fallback, absolute path only)
  4. <claude-config-dir>/vbw/debug-target.txt (user-global fallback, absolute path only; <claude-config-dir> is resolved by scripts/resolve-claude-dir.sh: CLAUDE_CONFIG_DIR if set, else $HOME/.config/claude-code when that directory exists, else $HOME/.claude)
  5. If none are configured, ask the user for the target repo path — do not guess.

Read the full file on GitHub · 333 lines

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. 8d ago First seen · 333 lines · 5,343 tokens per session scan C 4d4229ac27ab

Subscribe to this mod's changes

vibe-better-with-claude-code-vbw AGENTS.md is an instructions file published in the GitHub repository swt-labs/vibe-better-with-claude-code-vbw (79 stars, last pushed 2mo ago), licensed MIT. It adds 5,343 tokens to every session, about $0.0267 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens