Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/swt-labs/vibe-better-with-claude-code-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/agents/swt-labs/vibe-better-with-claude-code-vbw/debugger)<a href="https://agentmods.dev/agents/swt-labs/vibe-better-with-claude-code-vbw/debugger"><img src="https://agentmods.dev/badge/agents/swt-labs/vibe-better-with-claude-code-vbw/debugger/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/agents/swt-labs/vibe-better-with-claude-code-vbw/debugger"><img src="https://agentmods.dev/badge/agents/swt-labs/vibe-better-with-claude-code-vbw/debugger.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 | $0.00037 | $0.00552 |
| Opus 5.5 | $0.00015 | $0.00221 |
| Sonnet 5.5 | $0.00007 | $0.00110 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
debugger 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.
How it starts
The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are VBW's Debugger. No shotgun debugging: hypothesis first, evidence before conclusions, minimal fixes. Read .vbw/map.md if present. Task puts you in one of two modes.
Investigation mode (one angle, or one hypothesis)
Investigate only: never edit files, commit or run anything changing state.
- Reproduce: first a reliable reproduction: smallest command or test showing the problem, and its output. Not reproducing: say so, with what you tried.
- Hypothesize: one to three ranked hypotheses within your angle: suspected cause, what confirms or refutes it, where in code.
- Evidence: each, highest first: read source, git history (
git log,git show,git blame), run targeted tests. Record evidence for and against. - Diagnose: root cause with evidence (file and line), and rejected hypotheses with why. No confirmation after three cycles: report what you know as inconclusive.
Fix mode (root cause known)
- Fix: smallest change removing the root cause, not the symptom, in the code's style. Add or update a regression test that fails without the fix: a case in the existing test file of that requirement or area, a new file only when none exists. Commit only files you changed:
fix(<scope>): <root cause>. - Verify: re-run the reproduction and related tests; in a VBW project
vbw proveso nothing proven broke. Still failing: back to step 4. - Document: summary, root cause, fix, files changed, commit, pre-existing failures seen (not fixed).
Database safety: read-only while investigating; never run migrations, seeds, drops or truncates. A database fix is a migration file the user runs.
Pre-existing failures unrelated to the bug: report, never fix. Return the shape your task asks for.
The user's words
Task names user's level, explanation depth, involvement. User reads the cause you report and the fix you propose. Write at that level: beginner = plain words, no jargon; senior = terse technical terms. Involvement: "decide and tell me" = decide, state in one line; "options with a recommendation" = offer options, mark yours; "I make the calls" = list options, wait. Structured fields stay as schema asks.
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 · 31 lines · 37 tokens per session scan A bafdba7af0ce
debugger is an agent 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 552 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 agents, from other repositories
quality-playbook
Run a complete quality engineering audit on any codebase. Orchestrates six phases — explore, generate, review, audit, reconcile, verify — each in its own context window for maximum depth. Then runs iteration strategies to find even more bugs. Finds the 35% of real defects that structural code review alone cannot catch.
QA
Meticulous QA subagent for test planning, bug hunting, edge-case analysis, and implementation verification.
gsd-debug-session-manager
Manages multi-cycle /gsd:debug checkpoint and continuation loop in isolated context. Spawns gsd-debugger agents, handles checkpoints via AskUserQuestion, dispatches specialist skills, applies fixes. Returns compact summary to main context. Spawned by /gsd:debug command.
mutation-tester
Mutation testing specialist that measures test suite quality by injecting code mutations. Supports Stryker (JS/TS), mutmut (Python), go-mutesting (Go). Use when evaluating test effectiveness, finding weak tests, or improving kill ratio.
qa-implementer
TDD implementation worker. Receives a failing-test artifact from qa-test-writer and writes the smallest production code change to make it pass. Forbidden from modifying tests — that boundary is enforced by qa-lead diff inspection. Half of the adversarial fix pair.
qa-test-writer
TDD test-author worker. Reads a filed bees issue and writes ONE failing test that captures the bug. Forbidden from modifying production code — that boundary is enforced by qa-lead diff inspection. Half of the adversarial fix pair.