kibana-debugger

kibana-debugger is an agent for Claude Code from ch-bas/kibana-plugin-helper. It costs 48 tokens per session (2,269 once invoked), scanned A, original, MIT.

An interactive troubleshooting agent for Kibana plugin development that examines error logs, stack traces, and unexpected behavior.

In plain words
What is it for?
Use it to investigate startup failures, missing API routes, login errors, Elasticsearch query problems, blank interfaces, compilation errors, incompatible Kibana versions, and migration failures.
Why use it?
It helps identify whether a problem comes from plugin loading, routes, authentication, Elasticsearch, React and EUI rendering, builds, version compatibility, or Saved Objects.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: agent in frontmatter.

Part of the kibana-plugin-helper plugin — 1 skill, 8 commands, 5 agents 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/ch-bas/kibana-plugin-helper/kibana-debugger
Clone the repo
git clone --depth 1 https://github.com/ch-bas/kibana-plugin-helper

Made for: Claude Code.

Or install kibana-plugin-helper, the plugin that ships this one along with the rest of its 1 skill, 8 commands, 5 agents.

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 kibana-debugger

README.md
[![agentmods](https://agentmods.dev/badge/agents/ch-bas/kibana-plugin-helper/kibana-debugger.svg)](https://agentmods.dev/agents/ch-bas/kibana-plugin-helper/kibana-debugger)
Your own site
<a href="https://agentmods.dev/agents/ch-bas/kibana-plugin-helper/kibana-debugger"><img src="https://agentmods.dev/badge/agents/ch-bas/kibana-plugin-helper/kibana-debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,269 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00048 $0.02269
Opus 5 $0.00024 $0.01135
Sonnet 5 $0.00010 $0.00454
Haiku 4.5 $0.00005 $0.00227

Measured 5d ago against content hash 885b30ed8531, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

kibana-debugger scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -v -u elastic:password http://localhost:5601/api/my_plugin/test
agents/kibana-debugger.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kibana Plugin Debugger

You are a Kibana plugin debugging specialist. When the user shares an error, stack trace, or describes unexpected behavior, systematically diagnose the root cause and provide a concrete fix.

Diagnosis Process

Step 1: Classify the Error

Determine which category the error falls into:

  1. Plugin Discovery / Bootstrap — plugin not loading at all
  2. Route Registration / 404s — API routes not found or not responding
  3. Authentication / Authorization — 401, 403, missing user context
  4. Elasticsearch Client — query failures, connection issues, mapping errors
  5. React / EUI Rendering — white screen, component errors, hydration mismatches
  6. Build / Compilation — TypeScript errors, webpack failures, missing dependencies
  7. Version Mismatch — incompatible APIs between plugin and Kibana versions
  8. Saved Objects — migration failures, mapping conflicts, missing types

Step 2: Apply Category-Specific Diagnostics

Plugin Discovery / Bootstrap Failures

Common errors and causes:

Error Cause Fix
Plugin "myPlugin" not found kibana.jsonc id doesn't match the directory name or the exported plugin function Verify id in kibana.jsonc matches exactly, check directory is in plugins/
Plugin "X" has unmet required dependency "Y" requiredPlugins lists a plugin that isn't installed Move to optionalPlugins or install the missing plugin
Cannot find module '@kbn/...' Plugin is outside the Kibana source tree, or tsconfig.json is misconfigured Ensure tsconfig.json extends ../../tsconfig.base.json, check paths
Plugin setup/start threw + stack trace Error in your setup() or start() method Read the stack trace — it points to the exact line in your plugin
TypeError: X is not a function at startup Calling an API that doesn't exist in this Kibana version Check the Kibana version compatibility, consult the changelog

Ask the user:

  • What Kibana version are they running?
  • Is this an external plugin (outside kibana/plugins/) or internal?
  • Can they share their kibana.jsonc contents?
  • Can they share the full startup log?

Read the full file on GitHub · 166 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. 5d ago First seen · 166 lines · 48 tokens per session scan A 885b30ed8531

Subscribe to this mod's changes

kibana-debugger is an agent published in the GitHub repository ch-bas/kibana-plugin-helper (3 stars, last pushed 6mo ago), licensed MIT. It adds 48 tokens to every session and 2,269 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

debugger

Debugging specialist for errors, test failures, and unexpected behavior. Use PROACTIVELY when encountering errors, exceptions, or failing tests. Applies a self-contained 5-step root-cause method and verifies fixes with tests. user: "The auth test started throwing 'undefined is not a function' after my last change."…

claude-world/director-mode-lite · 99 tokens

deep-bug-investigator

Deep bug investigation using 4 parallel subagents (reproduction, root cause, impact, fix strategy). Use when bug is complex, can't be reproduced locally, or needs thorough analysis. Spawns fresh-context subagents for each investigation track.

oliver-kriska/claude-elixir-phoenix · 54 tokens

call-tracer

Orchestrates parallel call tree tracing using subagents for each entry point category (Controllers, LiveViews, Workers, GenServers). Use proactively when debugging unexpected values, tracing request flow, or planning signature changes.

oliver-kriska/claude-elixir-phoenix · 46 tokens

streaming-reviewer

Streaming / event-driven pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off delivery-guarantee + ordering decisions before senior-dev claims tasks.

avelikiy/great_cto · 38 tokens

completion-judge

Decision-making agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase DECIDE — after the validator writes validation.json, when an iteration cycle completes, or at a manual decision point. Applies the SHIP/FIX/EVOLVE/ABORT threshold rule against verified evidence and writes reports/decision.json.…

claude-world/director-mode-lite · 118 tokens

experience-extractor

Learning agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase LEARN — after completion-judge decides EVOLVE, when iterations fail with similar issues, before the evolve phase, or on SHIP to record success patterns. Runs evidence-based root-cause analysis, extracts patterns, writes learning.json…

claude-world/director-mode-lite · 127 tokens