troubleshoot

A command for diagnosing and fixing an unhealthy Control Plane workload, which is a deployed application component.

In plain words
What is it for?
It is for investigating deployment failures such as memory exhaustion, image or secret errors, port mismatches, blocked traffic, failed health checks, and storage or scaling problems.
Why use it?
It gives a repeatable process for collecting evidence, finding the cause, proposing an exact fix, and checking recovery after approval.

Command

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 commands/controlplane-com/ai-plugin/troubleshoot
Clone the repo
git clone --depth 1 https://github.com/controlplane-com/ai-plugin
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 217 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00019 $0.00217
Opus 5 $0.00010 $0.00109
Sonnet 5 $0.00004 $0.00043
Haiku 4.5 $0.00002 $0.00022

Measured 2d ago against content hash 3c18f2f0d2eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

troubleshoot 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 2d 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/cpln/commands/troubleshoot.md · 17 lines

What it actually says

Diagnose and fix the Control Plane workload the user named.

Use the cpln-workload-troubleshooter agent — it loads the workload-troubleshooting skill (the full failure catalog) and works read-only first:

  1. Gather state — per-location deployments and readiness, events, and logs.
  2. Map the symptom to its root cause: OOMKilled, image pull, secret access, port mismatch, firewall, health probes, resource limits, autoscaling, termination, volumes, service-to-service, or dedicated load balancer.
  3. Present each issue as what's wrong (with evidence), why, and the exact fix.
  4. Apply only after I approve, then re-check readiness across locations and confirm the endpoint responds.

If no workload was named, ask for it (and the GVC) — never guess.

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. 2d ago First seen · 17 lines · 19 tokens per session scan A 3c18f2f0d2eb

Subscribe to this mod's changes

troubleshoot is a command published in the GitHub repository controlplane-com/ai-plugin (10 stars, last pushed 8d ago), licensed MIT. It adds 19 tokens to every session and 217 once invoked, about $0.0001 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.