debug

A structured troubleshooting guide for platform problems across cloud services, Kubernetes, OpenShift, GitOps tools, networking, identity, and automated workflows.

In plain words
What is it for?
Use it to investigate symptoms such as pending pods, unreconciled releases, failed cloud authentication, workflow errors, or infrastructure problems.
Why use it?
It replaces guesswork with evidence collection, a likely root cause, a proposed fix, validation steps, and a way to roll back.

Command

Part of the platform-skills plugin — 1 skill, 43 commands, 1 agent 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 commands/nitinjain999/platform-skills/debug
Clone the repo
git clone --depth 1 https://github.com/nitinjain999/platform-skills

Or install platform-skills, the plugin that ships this one along with the rest of its 1 skill, 43 commands, 1 agent.

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,305 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 $0.00032 $0.01305
Opus 5 $0.00016 $0.00652
Sonnet 5 $0.00006 $0.00261
Haiku 4.5 $0.00003 $0.00130

Measured 3d ago against content hash 4939defbf460, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug 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 3d 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.

commands/debug.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.


Interactive Wizard (fires when $ARGUMENTS is empty)

When invoked with no arguments, ask before troubleshooting:

Q1 — What is the symptom?

Describe what's broken — paste the error message, command output, or describe
the observable behaviour (e.g. "pods stuck in Pending", "HelmRelease not reconciling",
"403 on IAM role assumption"):

Use the response as the symptom for all subsequent steps. Do not ask for the layer — infer it from the symptom description and show your classification in step 1.


You are a senior platform engineer performing structured troubleshooting.

The user reports: $ARGUMENTS

Follow this exact structure:

1. Classify the Layer

Identify which layer owns this problem:

  • Terraform — bootstrap, cloud resource, identity, networking
  • Kubernetes — workload, RBAC, policy, scheduling
  • OpenShift — SCC, route, operator, quota
  • Flux CD — source, artifact, reconciliation, chart rendering, runtime
  • Argo CD — sync, diff, project, health
  • Linkerd — proxy injection, mTLS, authorization policy, multi-cluster
  • GitHub Actions — workflow syntax, permissions, OIDC, runner
  • AWS / Azure — IAM, networking, managed service, quota
  • Secrets — ESO sync, Sealed Secrets, rotation

2. Evidence to Collect

List the exact commands the user should run to gather diagnostic data before any fix is attempted. Be specific — include namespace flags, resource names from the description, and output filters.

3. Root-Cause Hypothesis

Based on the symptom, state the most likely root cause. Explain why this layer and this cause. If multiple causes are plausible, rank them.

4. Proposed Fix

Provide the exact configuration change, command, or patch. Show before and after where relevant. Do not suggest a fix that requires evidence not yet collected.

5. Validation

Commands to confirm the fix worked.

6. Rollback

How to safely undo the change if validation fails.


Mode: timeline

Reconstruct what happened in a cluster in the last N minutes. Use when you know something broke but don't know when or what triggered it.

Read the full file on GitHub · 140 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. 3d ago First seen · 140 lines · 32 tokens per session scan A 4939defbf460

Subscribe to this mod's changes

debug is a command published in the GitHub repository nitinjain999/platform-skills (40 stars, last pushed 3d ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,305 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 2026-08-30.