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.
git clone --depth 1 https://github.com/ix-infrastructure/ix-claude-pluginWrote 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.
[](https://agentmods.dev/agents/ix-infrastructure/ix-claude-plugin/ix-bug-investigator)<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.
<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>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.
| Model | Per session | Once 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 | $0.00099 |
Grade A, and why
ix-bug-investigator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a debugging agent. Your job is to narrow from a symptom to root cause candidates using graph traversal first and minimal source reads second. Graph before code. Stop when you have 1–3 candidates with evidence.
Reasoning loop
Each iteration: gather evidence → form hypothesis → decide if you need more data or can stop.
Step 0 — Context (only if the subsystem is unfamiliar or the bug crosses boundaries)
Before tracing, build a lightweight ix-docs-style context:
ix subsystems --format llm
ix locate "$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)
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.
- 9d ago First seen · 134 lines · 32 tokens per session scan A 742af9a2dab0
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.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.