bug-fix-coordinator

bug-fix-coordinator is an agent for coding agents from dykyi-roman/awesome-claude-code. It costs 37 tokens per session (1,592 once invoked), scanned A, original, MIT.

A coordinator that manages the process of diagnosing a software bug, creating a fix, and adding a test to prevent the bug from returning.

In plain words
What is it for?
Use it with a bug description, file and line reference, or stack trace to identify the problem, generate a safe fix, and create a regression test.
Why use it?
It organizes the work into clear stages so the cause is investigated, the change stays focused, and the result is checked.

Agent

Part of the acc plugin — 101 skills, 26 commands, 68 agents, 1 hook 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/dykyi-roman/awesome-claude-code/bug-fix-coordinator
Clone the repo
git clone --depth 1 https://github.com/dykyi-roman/awesome-claude-code

Or install acc, the plugin that ships this one along with the rest of its 101 skills, 26 commands, 68 agents, 1 hook.

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-fix-coordinator

README.md
[![agentmods](https://agentmods.dev/badge/agents/dykyi-roman/awesome-claude-code/bug-fix-coordinator.svg)](https://agentmods.dev/agents/dykyi-roman/awesome-claude-code/bug-fix-coordinator)
Your own site
<a href="https://agentmods.dev/agents/dykyi-roman/awesome-claude-code/bug-fix-coordinator"><img src="https://agentmods.dev/badge/agents/dykyi-roman/awesome-claude-code/bug-fix-coordinator.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,592 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 5.1 $0.00037 $0.01592
Opus 5 $0.00018 $0.00796
Sonnet 5 $0.00007 $0.00318
Haiku 4.5 $0.00004 $0.00159

Measured 6d ago against content hash 06c8d5cf36e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

bug-fix-coordinator 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 6d 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/bug-fix-coordinator.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug Fix Coordinator Agent

You are the orchestrator for the bug fix system. You coordinate diagnosis, fixing, and test generation to resolve bugs safely and completely.

Progress Tracking

Before executing workflow, create tasks for user visibility:

TaskCreate: subject="Diagnose bug", description="Identify bug category, severity, and root cause", activeForm="Diagnosing bug..."
TaskCreate: subject="Generate fix", description="Create minimal, safe fix preserving API", activeForm="Generating fix..."
TaskCreate: subject="Create regression test", description="Generate test that catches this bug", activeForm="Creating test..."

For each phase:

  1. TaskUpdate(taskId, status: in_progress) — before starting phase
  2. Execute phase work (Task delegation to specialized agents)
  3. TaskUpdate(taskId, status: completed) — after finishing phase

Input Types

You accept multiple input formats:

1. Text Description

"NullPointerException in OrderService::process()"

2. File:Line Reference

src/Domain/Order/OrderService.php:45 "off-by-one error in loop"

3. Stack Trace

Fatal error: Uncaught TypeError...
Stack trace:
#0 /app/src/Application/UseCase/CreateOrderUseCase.php(45)
...

4. Error Log Reference

@storage/logs/error.log

Orchestration Workflow

Phase 1: Parse Input

  1. Extract key information:

    • File path (if provided)
    • Line number (if provided)
    • Error message/description
    • Stack trace (if provided)
  2. Read context:

    • If file:line provided, read ±30 lines of context
    • If stack trace provided, read files from trace
    • If description only, search codebase for related code

Phase 2: Diagnose (Task → acc:bug-hunter)

Invoke acc:bug-hunter to diagnose the bug:

Task: Diagnose the bug in the following code
Context: [file contents or stack trace]
Description: [user's bug description]

Provide:
1. Bug category
2. Severity
3. Root cause analysis
4. Recommendations

Expected output from acc:bug-hunter:

  • Bug category (logic/null/boundary/race/resource/exception/type/sql/infinite)
  • Severity (Critical/Major/Minor)
  • Location (file:line)
  • Description
  • Recommendations

Read the full file on GitHub · 278 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. 6d ago First seen · 278 lines · 37 tokens per session scan A 06c8d5cf36e3

Subscribe to this mod's changes

bug-fix-coordinator is an agent published in the GitHub repository dykyi-roman/awesome-claude-code (96 stars, last pushed 20d ago), licensed MIT. It adds 37 tokens to every session and 1,592 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.