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 redhuntlabs/wizard --skill troubleshooting-whats-not-workinggit clone --depth 1 https://github.com/redhuntlabs/wizardWrote 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/redhuntlabs/wizard/troubleshooting-whats-not-working)<a href="https://agentmods.dev/skills/redhuntlabs/wizard/troubleshooting-whats-not-working"><img src="https://agentmods.dev/badge/skills/redhuntlabs/wizard/troubleshooting-whats-not-working/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/redhuntlabs/wizard/troubleshooting-whats-not-working"><img src="https://agentmods.dev/badge/skills/redhuntlabs/wizard/troubleshooting-whats-not-working.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 | $0.00033 | $0.00974 |
| Opus 5 | $0.00016 | $0.00487 |
| Sonnet 5 | $0.00007 | $0.00195 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
troubleshooting-whats-not-working 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 11d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Troubleshooting What's Not Working
What this does
Walks you from "something is wrong" to a verified diagnosis using evidence, not guesses. Works for software bugs, broken appliances, stalled projects, or interpersonal issues.
When to use
- Something stopped working that used to work
- Something is producing the wrong result
- A plan isn't going as expected and you can't tell why
What you bring (Inputs)
- Description of what you expected to happen
- Description of what actually happened
- When it last worked / when the symptom started
What you get (Output)
A diagnosis (the cause) plus a verified fix attempt or, if unfixable yet, a clear "next thing to test."
How it works (Steps)
This is a guided workflow.
Stages
Stage 1: State the symptom precisely
Write one sentence: "When X, I expect Y, but I get Z." If you can't write this sentence, the symptom isn't precise enough yet. Sharpen.
Stage 2: Capture the recent change
What changed since this last worked? Be specific: "I updated the app" or "we moved offices" or "she started a new job." If "nothing changed," challenge that — something always did.
Stage 3: Bisect
Find the smallest scenario that still produces the symptom. Strip away anything optional. The smaller the failing case, the easier the cause is to see.
Stage 4: Form one hypothesis
State: "I think the cause is X because of evidence Y." One hypothesis at a time.
Stage 5: Test the hypothesis
Design a check that would prove the hypothesis wrong if it's wrong. Run the check. Record what you observed.
Stage 6: Decide
- Hypothesis confirmed → proceed to fix and verify the fix actually fixed it
- Hypothesis disproved → return to Stage 4 with a new hypothesis (don't recycle the old one)
- Hypothesis inconclusive → tighten the test in Stage 5
Stage 7: Verify the fix
After fixing: reproduce the original symptom scenario. The symptom must be gone. Otherwise the fix didn't fix it (despite what you'd like to believe).
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.
- 11d ago First seen · 110 lines · 33 tokens per session scan A d130df5808b6
troubleshooting-whats-not-working is a skill published in the GitHub repository redhuntlabs/wizard (9 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 974 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 2026-08-31.
Other skills, from other repositories
asc-crash-triage
Triage TestFlight crashes, beta feedback, and performance diagnostics using asc. Use when the user asks about TF crashes, TestFlight crash reports, beta tester feedback, app hangs, disk writes, launch diagnostics, or wants a crash summary for a build or app.
unicli-repair
Evidence-driven repair workflow for a broken Uni-CLI adapter. Trigger on a failed unicli envelope, a quarantined adapter, or an explicit adapter-repair request. Classifies non-source failures, edits only the reported adapter path, and uses the original command as a bounded oracle.
squid-architecture-review
Periodic architectural sweep — reads existing ADRs, maps modules/dependencies/layering, and reports up to 10 prioritised findings shaped as refactor proposals /squid-refactor can consume directly.
squid-triage-issue
Bug intake — localise the suspected code, capture a deterministic reproducer, and emit a groomed bug task with a regression-test acceptance criterion, ready for /squid-implement-task or the full pipeline.
squid-review-ci
Drive CI green on a pushed, review-clean feature PR — On-Call diagnoses failures and hands fix tasks to the SWE. Output: a CI-validated feature PR. Trigger after /squid-review passes.
dead-code-detector
Detect unused/unreachable code in polyglot codebases (Python, TypeScript, Rust). TRIGGERS - dead code, unused functions, unused imports.