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/kurrent-io/skillsWrote 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/kurrent-io/skills/troubleshooter)<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>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 | $0.00172 | $0.04361 |
| Opus 5 | $0.00086 | $0.02181 |
| Sonnet 5 | $0.00034 | $0.00872 |
| Haiku 4.5 | $0.00017 | $0.00436 |
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.
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, orAccessDeniedin 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-docsskill 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 atskills/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.
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.
- 7d ago First seen · 312 lines · 172 tokens per session scan A efe36424ae87
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.
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.
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.
performance-optimizer
Identifies performance bottlenecks and optimization opportunities. Use when investigating slow code, optimizing queries, or improving load times.
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.
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…
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…