deep-bug-investigator

deep-bug-investigator is an agent for Claude Code from oliver-kriska/claude-elixir-phoenix. It costs 54 tokens per session (2,832 once invoked), scanned A, original, MIT.

An investigation orchestrator that assigns a difficult bug to four focused sub-agents covering reproduction, cause, impact, and fix strategy.

In plain words
What is it for?
Use it for complex or hard-to-reproduce bugs after checking simple causes such as unsaved files, compilation errors, key mismatches, missing preloads, nil values, or invalid connection returns.
Why use it?
It divides broad debugging work into separate investigations so the evidence can be examined from several angles.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions subagents; names the NotebookEdit tool.

Part of the phx plugin — 50 skills, 26 agents, 10 hooks shipped together

Good fit Use it for complex or hard-to-reproduce bugs after checking simple causes such as unsaved files, compilation errors, key mismatches, missing preloads, nil values, or invalid connection returns.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/oliver-kriska/claude-elixir-phoenix/deep-bug-investigator
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.

Clone the repo
git clone --depth 1 https://github.com/oliver-kriska/claude-elixir-phoenix

Made for: Claude Code.

Or install phx, the plugin that ships this one along with the rest of its 50 skills, 26 agents, 10 hooks.

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 deep-bug-investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/oliver-kriska/claude-elixir-phoenix/deep-bug-investigator/github.svg)](https://agentmods.dev/agents/oliver-kriska/claude-elixir-phoenix/deep-bug-investigator)
Your own site
<a href="https://agentmods.dev/agents/oliver-kriska/claude-elixir-phoenix/deep-bug-investigator"><img src="https://agentmods.dev/badge/agents/oliver-kriska/claude-elixir-phoenix/deep-bug-investigator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for deep-bug-investigator

Your own site · 80×15
<a href="https://agentmods.dev/agents/oliver-kriska/claude-elixir-phoenix/deep-bug-investigator"><img src="https://agentmods.dev/badge/agents/oliver-kriska/claude-elixir-phoenix/deep-bug-investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,832 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 $0.00054 $0.02832
Opus 5 $0.00027 $0.01416
Sonnet 5 $0.00011 $0.00566
Haiku 4.5 $0.00005 $0.00283

Measured 10d ago against content hash 0938adff9b0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

deep-bug-investigator 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 10d 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.

plugins/elixir-phoenix/agents/deep-bug-investigator.md · 410 lines

How it starts

The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Bug Investigator (Parallel Orchestrator)

You orchestrate deep bug investigation by spawning 4 parallel subagents, each with fresh context for focused analysis.

Why Parallel Investigation

From Anthropic research:

  • Single agent loses focus on broad tasks (context degradation)
  • 4 parallel subagents each get fresh 200k context
  • Compression: each subagent explores deeply, returns condensed findings
  • Result: thorough analysis in ~1/4 wall-clock time

Quick Check First (Ralph Wiggum Mode)

Before spawning parallel tracks, check the obvious:

  1. Is the file saved? Does it compile? (mix compile --warnings-as-errors)
  2. Atom vs string key mismatch?
  3. Missing preload on association?
  4. Nil being passed where value expected?
  5. Conn/socket not returned from handler?
  6. Read the error message LITERALLY — what does it actually say?

If the quick check finds it, report and stop. No need for parallel tracks on obvious bugs.

Investigation Tracks (Parallel)

Track 1: Reproduction Subagent

Objective: Understand how to reproduce the bug

Focus areas:

  • Parse error messages, stack traces, logs
  • Identify reproduction steps
  • Create minimal test case
  • Document environment factors

Prompt template:

You are investigating bug reproduction for: {bug_description}

Your task:
1. Analyze the error message and stack trace
2. Identify the exact conditions that trigger the bug
3. Document step-by-step reproduction instructions
4. Create a minimal test case that demonstrates the issue
5. Note any environment-specific factors (Elixir version, deps, config)

Available information:
{error_message}
{stack_trace}
{user_reported_steps}

Report actionable findings — what to change and where. Skip background the synthesis step already has.

Output format:
## Reproduction Analysis
### Error Summary
### Reproduction Steps
### Minimal Test Case
### Environment Factors

Track 2: Root Cause Subagent

Objective: Find the actual bug location and why it happens

Read the full file on GitHub · 410 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. 10d ago First seen · 410 lines · 54 tokens per session scan A 0938adff9b0b

Subscribe to this mod's changes

deep-bug-investigator is an agent published in the GitHub repository oliver-kriska/claude-elixir-phoenix (542 stars, last pushed 4d ago), licensed MIT. It adds 54 tokens to every session and 2,832 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

bug-investigator

Use when a bug, regression, or unexpected behaviour needs its root cause traced to specific code before any fix is designed. Investigates only — never edits files. Returns a structured report citing file:line evidence.

kardebadas/claude-plugin · 46 tokens

performance-engineer

Profiles systems, identifies bottlenecks, optimizes code and infrastructure, and prevents performance regressions. Uses flame graphs, benchmarking, and data-driven analysis. Use when optimizing performance, investigating slow operations, setting performance budgets, or analyzing benchmarks.

saitarrun/Sdlc-ai-workflow · 52 tokens

craft-code-reviewer-deep

Deep code review on Opus 4.8 for high-stakes PRs — release branches, security-sensitive code, large architectural changes, migrations, multi-service flows. Use when extra scrutiny is worth the token cost; use craft-code-reviewer for daily review.

michtio/craftcms-claude-skills · 62 tokens

fec-performance-optimizer

Front-end performance analysis and optimization specialization: Core Web Vitals, packaging volume, runtime and rendering, network and cache, memory leak troubleshooting; can cooperate with Lighthouse, Bundle analysis and Profiler. Use it when users mention page slowness, lag, first screen, package size, poor…

bovinphang/frontend-craft · 0 tokens

fec-ui-checker

Use this subagent to troubleshoot visual defects, layout confusion, CSS issues, responsive exceptions, and inconsistencies between interaction and design in the front-end UI, and save the report as a Markdown file. Supports obtaining design data from Figma, Sketch, MasterGo, Pixso, Moko, and Mock, compares the design…

bovinphang/frontend-craft · 0 tokens

bulwark-implementer

Code-writing agent that implements fixes and features following Bulwark standards. Quality enforced by direct implementer-quality.sh invocation after each Write/Edit. Use proactively after a debug report (fix mode) or design document (feature mode) is ready for implementation.

QBall-Inc/the-bulwark · 57 tokens