troubleshooter

troubleshooter is an agent for Claude Code from kurrent-io/skills. It costs 172 tokens per session (4,361 once invoked), scanned A, original, Apache-2.0.

A read-only diagnostic agent for KurrentDB and EventStoreDB, databases that store events in ordered streams.

In plain words
What is it for?
Use it to investigate connection, TLS, subscription, cluster, projection, authentication, and event-append problems, then receive a cause, suggested fix, and verification step.
Why use it?
It helps narrow down runtime failures by classifying the symptom and following a relevant troubleshooting decision tree.

Agent for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the kurrent plugin — 6 skills, 3 agents shipped together

Good fit Use it to investigate connection, TLS, subscription, cluster, projection, authentication, and event-append problems, then receive a cause, suggested fix, and verification step.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kurrent-io/skills/troubleshooter
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/kurrent-io/skills

Made for: Claude Code.

Or install kurrent, the plugin that ships this one along with the rest of its 6 skills, 3 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 troubleshooter

README.md
[![agentmods](https://agentmods.dev/badge/agents/kurrent-io/skills/troubleshooter.svg)](https://agentmods.dev/agents/kurrent-io/skills/troubleshooter)
Your own site
<a href="https://agentmods.dev/agents/kurrent-io/skills/troubleshooter"><img src="https://agentmods.dev/badge/agents/kurrent-io/skills/troubleshooter.svg" alt="Measured on agentmods" height="20"></a>
Per session 172 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,361 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 $0.00172 $0.04361
Opus 5 $0.00086 $0.02181
Sonnet 5 $0.00034 $0.00872
Haiku 4.5 $0.00017 $0.00436

Measured 7d ago against content hash efe36424ae87, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

troubleshooter 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.

plugins/kurrent/agents/troubleshooter.agent.md · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KurrentDB Troubleshooter

You diagnose KurrentDB / EventStoreDB runtime failures by classifying the symptom, gathering the relevant state, walking a decision tree for that failure mode, and producing a graded report with cause, fix, and a verification step. You are a read-only diagnostic agent. You do not edit application source, mutate cluster configuration, or run destructive operations; you observe, classify, and recommend.

When to invoke

  • Connection failures. User says "my app can't connect to my cluster", "TLS handshake failed", "the client times out on startup", or "connection refused on 2113". Classify between network, TLS, discovery, auth, and parse failures; walk the connectivity tree.
  • Production runtime errors. User reports WrongExpectedVersion, NotLeader, DEADLINE_EXCEEDED, StreamDeleted, or AccessDenied in production logs. Walk the append, subscription, or auth tree depending on which surface raised the error.
  • Subscription lag or drop. User says "subscription is lagging behind $all", "persistent subscription is parking messages", "checkpoint isn't advancing", or "live mode never engages". Walk the subscription tree.
  • Cluster misbehaviour. User reports "cluster won't elect a leader", "gossip is partitioned", "scavenge is hanging", "disk is filling up", or "one node keeps falling behind". Walk the cluster-health or operations tree.

When not to use

  • User wants a static code review on SDK call sites (use code-reviewer).
  • User wants to migrate off the legacy TCP client or rebrand connection strings (use migration-specialist).
  • User wants conceptual documentation or a tutorial (use the kurrent-docs skill directly).
  • The failure is a build or compilation error, not a runtime error (project's own build tooling).

Skills used

Load only the references each finding cites. Do not pre-load the whole skill.

  • kurrentdb-client-detection. Inventory the application's client surface (package version, transport, connection string scheme, TLS posture). Always call first when the symptom touches the client.
  • kurrentdb-server-detection. Inventory the deployed cluster (version, topology, license posture, TLS posture). Always call first when the symptom touches the server.
  • kurrent-docs. The router lives at skills/kurrent-docs/SKILL.md; load the matching reference for the failure mode you have classified. Decision trees below cite the exact path.
  • kurrentdb-connection. Load this when the finding is "the client is misconfigured" rather than "the cluster is broken": connection-string parameters, nodePreference, keepalive, deadlines, serverless client reuse, and connection-error triage from the client side.

Read the full file on GitHub · 312 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 · 312 lines · 172 tokens per session scan A efe36424ae87

Subscribe to this mod's changes

troubleshooter is an agent published in the GitHub repository kurrent-io/skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 172 tokens to every session and 4,361 once invoked, about $0.0009 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.

Related

Other agents, from other repositories

database-optimizer

Optimize SQL queries, design efficient indexes, and handle database migrations. Solves N+1 problems, slow queries, and implements caching. Use PROACTIVELY for database performance issues or schema optimization.

davepoon/buildwithclaude · 44 tokens

d1-debugger

Autonomous diagnostic agent that investigates Cloudflare D1 database issues through 9-phase analysis (config, migrations, queries, bindings, errors, limits, performance, Time Travel, report). Use when encountering D1 query errors, migration failures, binding issues, performance degradation, or limit/quota errors.

secondsky/claude-skills · 65 tokens

performance-optimizer

Identifies performance bottlenecks and optimization opportunities. Use when investigating slow code, optimizing queries, or improving load times.

travisjneuman/.claude · 28 tokens

doctrine-performance-optimizer

Read-only performance audit of Doctrine usage: N+1 queries, fetch modes, batch processing, missing indexes, and caching opportunities. Use proactively after adding entities, relations, repository queries, or when a page/endpoint is reported slow.

dev-toolings/superpowers-symfony · 53 tokens

sqlscript-analyzer

Use this agent when the user asks to "analyze my SQLScript", "review HANA procedure", "check procedure performance", "find SQLScript issues", "audit SQLScript code", "review stored procedure", or needs performance analysis of SAP HANA database procedures. Examples: Context: User has written a SQLScript procedure and…

secondsky/sap-skills · 329 tokens

db-performance-auditor

Audits a .NET data-access layer end to end for performance — EF Core query patterns (N+1, projections, tracking), indexing gaps, DbContext configuration, connection resiliency, and bulk-operation opportunities — and produces a ranked report with fixes. Use when the user wants a database/EF performance review of a…

StefanTheCode/dotnet-ai-toolkit · 88 tokens