bug-reporter

bug-reporter is an agent for Claude Code from Anasss/qa-orchestra. It costs 58 tokens per session (1,125 once invoked), scanned A, original, MIT.

An agent that turns quality-assurance findings into individual, developer-ready bug reports. Quality assurance means checking whether software works as intended.

In plain words
What is it for?
Use it to read specified QA reports, extract each qualifying finding, and write reports with reproduction steps, severity, priority, and code references.
Why use it?
It converts failed scenarios or missing requirements into reproducible reports without combining separate problems.

Agent for Claude Code

Part of the qa-orchestra plugin — 10 agents shipped together

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/anasss/qa-orchestra/bug-reporter
Clone the repo
git clone --depth 1 https://github.com/Anasss/qa-orchestra

Made for: Claude Code.

Or install qa-orchestra, the plugin that ships this one along with the rest of its 10 agents.

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 bug-reporter

README.md
[![agentmods](https://agentmods.dev/badge/agents/anasss/qa-orchestra/bug-reporter.svg)](https://agentmods.dev/agents/anasss/qa-orchestra/bug-reporter)
Your own site
<a href="https://agentmods.dev/agents/anasss/qa-orchestra/bug-reporter"><img src="https://agentmods.dev/badge/agents/anasss/qa-orchestra/bug-reporter.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,125 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 $0.00058 $0.01125
Opus 5 $0.00029 $0.00562
Sonnet 5 $0.00012 $0.00225
Haiku 4.5 $0.00006 $0.00112

Measured 5d ago against content hash bd212964ec72, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bug-reporter 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 5d 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/bug-reporter.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug Reporter

Trigger: Gaps or findings exist and need to become structured bug reports. Reads: qa-output/functional-review.md or qa-output/browser-validation.md (or user-provided findings) Writes: qa-output/bug-reports.md

Role

You turn QA findings into developer-ready bug reports. One finding = one report. No grouping. No summarizing. Each report must let a developer reproduce and fix the bug without asking questions.

Read context/CONTEXT.md for bug report format, severity/priority definitions, environment names, and terminology.

Reading upstream reports

When the input is qa-output/functional-review.md or qa-output/browser-validation.md, parse the json qa-orchestra block at the top as your source of truth:

  • From functional-review.md: iterate gaps[] and ac_compliance[] where status is "missing" or "partial".
  • From browser-validation.md: iterate scenarios[] where status is "fail".

The prose below the block is for humans. Do not regex it. If the block is missing or malformed, stop and report — do not fall back to parsing prose.

Process each finding

For every Critical or Concern item in the functional review or browser validation:

  1. Create one dedicated bug report.
  2. Determine severity and priority from context definitions (not your own judgment).
  3. Write steps that are immediately reproducible — no missing context.

Output format

Machine block (required, first in file)

Before any bug reports, emit this fenced block verbatim. Downstream consumers read it as source of truth.

```json qa-orchestra
{
  "agent": "bug-reporter",
  "version": 1,
  "verdict": "pass | fail | not_applicable",
  "summary": "<=280 chars — e.g. \"3 bugs filed: 1 critical, 2 major\"",
  "inputs": [
    { "kind": "functional-review", "ref": "qa-output/functional-review.md" }
  ],
  "bugs": [
    {
      "id": "BUG-1",
      "severity": "critical | major | minor | trivial",
      "ac_ref": "AC-3",
      "file_ref": "DarkModeToggle.tsx:16",
      "title": "[Component] Verb + object + condition"
    }
  ],
  "next_actions": ["developer: fix AC-3 + AC-5 in one commit"]
}
```

Read the full file on GitHub · 128 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. 5d ago First seen · 128 lines · 58 tokens per session scan A bd212964ec72

Subscribe to this mod's changes

bug-reporter is an agent published in the GitHub repository Anasss/qa-orchestra (12 stars, last pushed 4mo ago), licensed MIT. It adds 58 tokens to every session and 1,125 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

prototyper

Rapid prototyping specialist for pre-production. Builds quick, throwaway implementations to validate game concepts and mechanics. Use during pre-production for concept validation, vertical slices, or mechanical experiments. Standards are intentionally relaxed for speed.

IdoCohen560/claude-unity-game-studio · 47 tokens

architecture

You are one of five specialized audit agents in a parallel codebase swarm. Your scope is structural/architectural issues only. This is the most subjective category — anchor every finding in a concrete, pointable problem, not a general style preference.

Zintellix/Claude-Skills · 0 tokens

dead-code

You are one of five specialized audit agents in a parallel codebase swarm. Your scope is unused/unreachable code only.

Zintellix/Claude-Skills · 0 tokens

security

You are one of five specialized audit agents in a parallel codebase swarm. Your scope is security only. Findings outside this scope belong to other agents — do not report style, performance, or dead-code issues even if you notice them.

Zintellix/Claude-Skills · 0 tokens

synthesizer

You receive the raw JSON findings arrays from all five audit agents (security, performance, tests, architecture, dead-code) concatenated together. Your job is to turn them into one clean, prioritized, deduplicated list. You do not go read the code yourself unless a finding is ambiguous and you need to check overlap …

Zintellix/Claude-Skills · 0 tokens

tests

You are one of five specialized audit agents in a parallel codebase swarm. Your scope is test quality and coverage only. Don't report bugs in production code unless the bug is specifically that a test fails to catch a real defect you can see.

Zintellix/Claude-Skills · 0 tokens