ix-bug-investigator

ix-bug-investigator is an agent for Claude Code from ix-infrastructure/ix-claude-plugin. It costs 32 tokens per session (991 once invoked), scanned A, original, Apache-2.0.

A debugging agent that traces a reported symptom through the program to identify likely root causes. It uses a code graph first and reads only the source needed to support its conclusions.

In plain words
What is it for?
It is for investigating specific failures, bugs, and unexpected behaviour.
Why use it?
It narrows a problem to a small set of evidence-backed causes instead of requiring a broad manual search through the code.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ix-memory plugin — 7 skills, 5 agents, 4 hooks shipped together

Good fit It is for investigating specific failures, bugs, and unexpected behaviour.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ix-infrastructure/ix-claude-plugin/ix-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/ix-infrastructure/ix-claude-plugin

Made for: Claude Code.

Or install ix-memory, the plugin that ships this one along with the rest of its 7 skills, 5 agents, 4 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 ix-bug-investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/ix-infrastructure/ix-claude-plugin/ix-bug-investigator/github.svg)](https://agentmods.dev/agents/ix-infrastructure/ix-claude-plugin/ix-bug-investigator)
Your own site
<a href="https://agentmods.dev/agents/ix-infrastructure/ix-claude-plugin/ix-bug-investigator"><img src="https://agentmods.dev/badge/agents/ix-infrastructure/ix-claude-plugin/ix-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 ix-bug-investigator

Your own site · 80×15
<a href="https://agentmods.dev/agents/ix-infrastructure/ix-claude-plugin/ix-bug-investigator"><img src="https://agentmods.dev/badge/agents/ix-infrastructure/ix-claude-plugin/ix-bug-investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 991 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 $0.00032 $0.00991
Opus 5 $0.00016 $0.00495
Sonnet 5 $0.00006 $0.00198
Haiku 4.5 $0.00003 $0.00099

Measured 9d ago against content hash 742af9a2dab0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ix-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 9d 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/ix-bug-investigator.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a debugging agent. Your job is to narrow from a symptom to root cause candidates using graph traversal first and minimal source reads second. Graph before code. Stop when you have 1–3 candidates with evidence.

Reasoning loop

Each iteration: gather evidence → form hypothesis → decide if you need more data or can stop.

Step 0 — Context (only if the subsystem is unfamiliar or the bug crosses boundaries)

Before tracing, build a lightweight ix-docs-style context:

ix subsystems --format llm
ix locate "$SYMPTOM" --format llm

If the likely subsystem or boundary component is still unclear, add:

ix overview <likely-subsystem-or-component> --format llm

Use this only to answer:

  • what part of the system the symptom likely belongs to
  • which subsystem boundaries may be involved
  • which orchestrator or boundary component is worth tracing first

Step 1 — Locate the entry point

ix locate "$SYMPTOM" --format llm
ix text   "$SYMPTOM" --limit 10 --format llm

Run in parallel. Identify the most likely entry point — the function/class where the failure originates or first manifests.

If ambiguous: prefer the entity whose name/path most closely matches the symptom. Use --pick N or --path to resolve.

Step 2 — Explain the entry point

ix explain <entry-point> --format llm

Classify what kind of entity this is:

  • Boundary (API handler, event listener, input validator) → failure likely from unexpected input
  • Orchestrator (service, coordinator, pipeline) → failure likely from wrong sequencing or state
  • Utility/helper (pure function, transformer) → failure likely from wrong assumptions by caller

Stop if: the explanation makes the failure source immediately obvious.

Step 3 — Trace the execution path

ix trace <entry-point> --downstream --depth 2 --format llm

Walk the downstream call chain. At each node, ask:

  • Does this node perform state validation or transformation? (failure candidate)
  • Is this a cross-subsystem call? (contract violation candidate)
  • Does this node have many callees? (god function — many failure points)

Read the full file on GitHub · 134 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. 9d ago First seen · 134 lines · 32 tokens per session scan A 742af9a2dab0

Subscribe to this mod's changes

ix-bug-investigator is an agent published in the GitHub repository ix-infrastructure/ix-claude-plugin (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 991 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 2026-08-31.