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.
npx skills add nitinjain999/platform-skills --skill debuggit clone --depth 1 https://github.com/nitinjain999/platform-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/skills/nitinjain999/platform-skills/debug)<a href="https://agentmods.dev/skills/nitinjain999/platform-skills/debug"><img src="https://agentmods.dev/badge/skills/nitinjain999/platform-skills/debug/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nitinjain999/platform-skills/debug"><img src="https://agentmods.dev/badge/skills/nitinjain999/platform-skills/debug.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00032 | $0.01305 |
| Opus 5.5 | $0.00013 | $0.00522 |
| Sonnet 5.5 | $0.00006 | $0.00261 |
| Haiku 4.5 | $0.00003 | $0.00130 |
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 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.
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 — 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.
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.
- 5d ago First seen · 140 lines · 32 tokens per session scan A 4939defbf460
debug is a skill published in the GitHub repository nitinjain999/platform-skills (70 stars, last pushed 3d ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,305 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-12.
Other skills, from other repositories
ia-c-systems
C patterns for systems code, libraries, and native extensions: module layout, function decomposition, status-enum errors, memory safety, undefined behavior, and performance measurement. Use when writing, reviewing, refactoring, or debugging C, working with malloc lifetimes, buffer overflows, sanitizers, or Valgrind…
ia-verification-before-completion
Enforces fresh verification evidence before any completion claim. Use when about to claim "tests pass", "bug fixed", "done", "ready to merge", handing off work, or before editing when a request has ambiguous scope.
debugging
Systematic root-cause debugging: reproduce, investigate, hypothesize, fix with verification. Use when asked to "debug this", "fix this bug", "why is this failing", "troubleshoot", or mentions errors, stack traces, broken tests, flaky tests, regressions, or unexpected behavior.
rubber-ducky
Use when you've planned a non-trivial change and are about to implement it, finished a complex or multi-file piece of work, just wrote tests, or are stuck on repeated failures — and any time the user says "rubber duck this", "rubber ducky", "get a second opinion", "sanity-check my plan", "poke holes in this", "what am…
analyze-misfires
Analyze Whetstone skill injection misfires when asked to investigate overly broad triggers or irrelevant injected skills.
diagnose-negatives
Investigate negative session feedback for a Whetstone skill when asked to diagnose its failures.