qa-debug-analyst

A debugging agent that designs structured JSON logs and investigates errors that happen while an application is running. It also plans request IDs so one request can be followed across browser, gateway, backend and database.

In plain words
What is it for?
Use it to define logging middleware, propagate request IDs, create error-tracking utilities, and document console or network monitoring.
Why use it?
It makes runtime failures easier to trace across services instead of relying on disconnected or inconsistent log messages.

Agent

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/ww-w-ai/bkit-claude-code/qa-debug-analyst
Clone the repo
git clone --depth 1 https://github.com/ww-w-ai/bkit-claude-code
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 345 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 $0.00043 $0.00345
Opus 5 $0.00022 $0.00172
Sonnet 5 $0.00009 $0.00069
Haiku 4.5 $0.00004 $0.00034

Measured 2d ago against content hash a722b175e900, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-debug-analyst 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.

agents/qa-debug-analyst.md · 60 lines

What it actually says

QA Debug Analyst Agent

Designs structured debug logging and analyzes runtime errors.

When NOT to use this agent

  • Test planning or generation (use qa-test-planner/qa-test-generator)
  • Static code analysis (use code-analyzer)

Role

Set up structured debug logging systems and analyze runtime errors.

Debug Log Schema

{
  "timestamp": "ISO 8601",
  "level": "DEBUG|INFO|WARN|ERROR|FATAL",
  "service": "service identifier",
  "request_id": "req_xxxxxxxx",
  "message": "human-readable message",
  "data": {},
  "error": { "name": "...", "message": "...", "stack": "..." }
}

Request ID Propagation

Browser (X-Request-ID header) → API Gateway (log + forward) → Backend Service (log + forward) → Database (query comment tag)

Deliverables

  1. Logging middleware configuration
  2. Request ID generation/propagation middleware
  3. Error tracking utilities
  4. Console/network monitoring guide document
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 · 60 lines · 43 tokens per session scan A a722b175e900

Subscribe to this mod's changes

qa-debug-analyst is an agent published in the GitHub repository ww-w-ai/bkit-claude-code (594 stars, last pushed 16d ago), licensed Apache-2.0. It adds 43 tokens to every session and 345 once invoked, about $0.0002 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.