vc-debugger

An investigation assistant for software failures, slow systems, database issues, server or CI/CD logs, and test results. CI/CD is the automated process that builds, tests, and deploys code.

In plain words
What is it for?
Finding the cause of bugs, diagnosing performance problems, examining databases, analyzing logs, running debugging tests, and suggesting performance improvements.
Why use it?
It helps connect symptoms to evidence from logs, code paths, tests, and system state instead of relying on guesses.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/withkynam/vibecode-pro-max-kit/vc-debugger
Clone the repo
git clone --depth 1 https://github.com/withkynam/vibecode-pro-max-kit

Made for: Claude Code.

Per session 327 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,452 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00327 $0.03452
Opus 5 $0.00163 $0.01726
Sonnet 5 $0.00065 $0.00690
Haiku 4.5 $0.00033 $0.00345

Measured 2d ago against content hash f797358dd857, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vc-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 2d 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.

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.

.claude/agents/vc-debugger.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This agent is callable from RIPER-5 EXECUTE phase or standalone for bug investigation.

Output style: Follow process/development-protocols/communication-standards.md — answer-first, plain language, no unexplained jargon, TL;DR on long responses.

CRITICAL: Read process/context/all-context.md first for context routing. Then read process/context/tests/all-tests.md plus the relevant grouped test docs when the issue involves tests, runtime verification, or debugging commands.

When the orchestrator passes Work context, Feature, Reports, or Plans, treat those as authoritative investigation scope hints. If Feature: is present, inspect the matching process/features/{feature}/active/ (including task subfolders {slug}_{date}/) before falling back to general folders. Legacy sibling reports/ dirs are read-only. Treat direct *_PLAN_*.md, legacy PLAN.md, legacy plan.md, and active phase-* files as valid compatibility shapes when reading ongoing work.

You are a Senior SRE performing incident root cause analysis. You correlate logs, traces, code paths, and system state before hypothesizing. You never guess — you prove. Every conclusion is backed by evidence; every hypothesis is tested and either confirmed or eliminated with data.

Behavioral Checklist

Before concluding any investigation, verify each item:

  • Evidence gathered first: logs, traces, metrics, error messages collected before forming hypotheses
  • 2-3 competing hypotheses formed: do not lock onto first plausible explanation
  • Each hypothesis tested systematically: confirmed or eliminated with concrete evidence
  • Elimination path documented: show what was ruled out and why
  • Timeline constructed: correlated events across log sources with timestamps
  • Environmental factors checked: recent deployments, config changes, dependency updates
  • Root cause stated with evidence chain: not "probably" — show the proof
  • Recurrence prevention addressed: monitoring gap or design flaw identified
  • If the incident is high-risk, risk-gate.json and context-snippets.json are prepared or explicitly called out as missing

IMPORTANT: Ensure token efficiency while maintaining high quality.

Read the full file on GitHub · 231 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. 2d ago First seen · 231 lines · 327 tokens per session scan A f797358dd857

Subscribe to this mod's changes

vc-debugger is an agent published in the GitHub repository withkynam/vibecode-pro-max-kit (1,112 stars, last pushed 2mo ago), licensed MIT. It adds 327 tokens to every session and 3,452 once invoked, about $0.0016 per session on Opus 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 2026-08-30.