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 jonZlotnik/how-to-agent --skill fix-the-problem-not-the-blamegit clone --depth 1 https://github.com/jonZlotnik/how-to-agentWrote 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/jonzlotnik/how-to-agent/fix-the-problem-not-the-blame)<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/fix-the-problem-not-the-blame"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/fix-the-problem-not-the-blame/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/jonzlotnik/how-to-agent/fix-the-problem-not-the-blame"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/fix-the-problem-not-the-blame.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 | $0.00056 | $0.00633 |
| Opus 5 | $0.00028 | $0.00316 |
| Sonnet 5 | $0.00011 | $0.00127 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
fix-the-problem-not-the-blame 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix the Problem, Not the Blame
The goal of debugging is to understand. Blaming the compiler, the OS, the library, "flaky tests", or the user is almost always wrong and always premature. Start from the assumption that your code is the culprit, gather facts, and let the evidence — not intuition — drive the fix.
When to use
- Any bug, test failure, or "it worked yesterday" report
- A symptom is reproducible but its cause is unclear
- You're tempted to wrap something in a try/except, retry, or
if not Nonecheck to make it go away - A teammate or LLM suggests "must be a flake, just rerun"
Protocol
- Don't panic. Take ten seconds. Panic-debugging spreads damage to working code.
- Reproduce reliably before changing anything. If you can't trigger it on demand, you can't verify the fix. Capture the minimal repro.
- Read the actual error. Not the summary, not what you expect — the literal message, the literal stack, the literal values. Half of bugs surrender here.
- Default suspicion to your own code. Libraries and platforms have bugs, but they're rare compared to yours. Eliminate yours first.
- Form one hypothesis at a time. Predict what you'd see if it's true. Test that prediction with a check that can fail. Update; don't accumulate.
- Find the root cause, not a symptom that disappears. A fix you can't explain is a fix that will return.
Red flags (rationalizations to reject)
- "It must be a compiler bug." — Almost never. Look again.
- "The test is flaky." — Sometimes true. More often the test exposes a real race or order dependency you don't want to face.
- "Adding a retry / try-except makes it pass." — Pass is not fix. You hid a problem that will resurface louder.
- "I don't know why this works now." — Then it doesn't work. See [[prove-dont-assume]].
- "Good enough, ship it." — A bug you don't understand will pick its own moment to reappear.
Composes with
- [[prove-dont-assume]] — every step of the hypothesis must be verified, not believed.
- [[listen-to-nagging-doubts]] — the "this still feels off" feeling after a green test is data; chase it.
- [[crash-early]] — once the root cause is known, replace any masking handler with a hard failure so future occurrences are loud.
- [[design-by-contract]] — if a precondition was silently violated, add the contract so the next violation is impossible to ignore.
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 · 40 lines · 56 tokens per session scan A 04d0f010ac59
fix-the-problem-not-the-blame is a skill published in the GitHub repository jonZlotnik/how-to-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 633 once invoked, about $0.0003 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.