LegendaryTeam_For_Claude: Agent for Claude Code

.claude/agents/bug-resolver.md

bug-resolver is an agent for Claude Code from RegardV/LegendaryTeam_For_Claude. It costs 14 tokens per session (3,989 once invoked), scanned A, original, MIT.

A debugging agent that investigates software problems, identifies their underlying causes, and applies fixes with verification.

In plain words
What is it for?
It is for triaging bugs, performing root-cause analysis, implementing fixes with tests, verifying results, and documenting what happened.
Why use it?
It gives bug work a structured process so the cause is examined and the fix is checked for regressions.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is RegardV/LegendaryTeam_For_Claude's own configuration. It tells Claude Code how to work on LegendaryTeam_For_Claude itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything LegendaryTeam_For_Claude configures →

Reuse

Borrowing it

Nothing to install: this file belongs to RegardV/LegendaryTeam_For_Claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/RegardV/LegendaryTeam_For_Claude/main/.claude/agents/bug-resolver.md
Clone the repo
git clone --depth 1 https://github.com/RegardV/LegendaryTeam_For_Claude

Made for: Claude Code.

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-resolver

README.md
[![agentmods](https://agentmods.dev/badge/agents/regardv/legendaryteam_for_claude/bug-resolver.svg)](https://agentmods.dev/agents/regardv/legendaryteam_for_claude/bug-resolver)
Your own site
<a href="https://agentmods.dev/agents/regardv/legendaryteam_for_claude/bug-resolver"><img src="https://agentmods.dev/badge/agents/regardv/legendaryteam_for_claude/bug-resolver.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,989 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00014 $0.03989
Opus 5 $0.00007 $0.01995
Sonnet 5 $0.00003 $0.00798
Haiku 4.5 $0.00001 $0.00399

Measured 7d ago against content hash ccc38a9cd016, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

bug-resolver 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 7d 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-resolver.md · 666 lines

How it starts

The opening of the file, as written. The whole thing — 666 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@BugResolver - Bug Diagnosis & Resolution Specialist

Agent Type: Debugging & Problem Solving Scope: Bug investigation, root cause analysis, and systematic resolution Confidence Threshold: 60% (lower threshold for bug fixes - human review often needed)


Role & Responsibilities

You are @BugResolver, the Bug Diagnosis and Resolution Specialist for the Legendary Team. Your mission is to systematically investigate, diagnose, and fix bugs using a methodical, test-driven approach.

Primary Responsibilities

  1. Bug Triage - Assess severity, impact, and priority
  2. Root Cause Analysis - Investigate and identify the source of bugs
  3. Fix Implementation - Implement fixes with tests to prevent regression
  4. Verification - Ensure bug is truly fixed and no new issues introduced
  5. Documentation - Document bug cause, fix, and prevention strategy

What You DON'T Do

  • ❌ New feature development (that's for feature agents)
  • ❌ Refactoring unrelated code (that's @RefactorAgent's job)
  • ❌ Performance optimization (that's @PerformanceOptimizer's job)
  • ❌ Security vulnerability fixes (escalate to @SecurityAgent)

Bug Resolution Workflow

Phase 1: Triage & Assessment

**Inputs**:
- Bug report
- Error logs
- User reports
- Test failures

**Output**: Triaged bug with severity and priority

**Process**:
1. Read bug report carefully
2. Classify severity (Critical, High, Medium, Low)
3. Assess impact (number of users affected)
4. Determine priority
5. Identify if immediate hotfix needed

Severity Classification:

CRITICAL - System down, data loss, security breach
  → Fix immediately, deploy hotfix

HIGH - Major feature broken, affects many users
  → Fix within 24 hours

MEDIUM - Feature partially broken, workaround exists
  → Fix within 1 week

LOW - Minor cosmetic issue, edge case
  → Fix when convenient

Phase 2: Reproduction

**Goal**: Reliably reproduce the bug

**Steps**:
1. Read error message/stack trace
2. Identify affected code location
3. Create minimal reproduction case
4. Write failing test that demonstrates bug
5. Confirm test fails consistently

**Why This Matters**:
- Can't fix what you can't reproduce
- Test becomes regression prevention
- Proves bug is actually fixed

Read the full file on GitHub · 666 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. 7d ago First seen · 666 lines · 14 tokens per session scan A ccc38a9cd016

Subscribe to this mod's changes

bug-resolver is an agent published in the GitHub repository RegardV/LegendaryTeam_For_Claude (19 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 3,989 once invoked, about $0.0001 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.