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 this-is-tobi/tools --skill systematic-debugginggit clone --depth 1 https://github.com/this-is-tobi/toolsWrote 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/this-is-tobi/tools/systematic-debugging)<a href="https://agentmods.dev/skills/this-is-tobi/tools/systematic-debugging"><img src="https://agentmods.dev/badge/skills/this-is-tobi/tools/systematic-debugging/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/this-is-tobi/tools/systematic-debugging"><img src="https://agentmods.dev/badge/skills/this-is-tobi/tools/systematic-debugging.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 | $0.00064 | $0.00737 |
| Opus 5.5 | $0.00026 | $0.00295 |
| Sonnet 5.5 | $0.00013 | $0.00147 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
systematic-debugging 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 2mo 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
Quick fixes that don't hold are almost always caused by skipping a step below, not by the bug being unusually hard. Work the steps in order; don't jump to a fix before step 3.
1. Reproduce reliably first
- Find the smallest input/action that triggers the bug every time. A bug you can't reproduce on demand can't be verified as fixed.
- If it's intermittent, capture the conditions that vary between runs that succeed and runs that fail (timing, ordering, state, environment) before doing anything else.
2. Read the actual failure, not your assumption of it
- Read the full error/stack trace, not just the top line — the real fault is often several frames away from where it surfaced.
- Check what the code actually does at the failure point (via the debugger, logs, or a print/assert), not what you expect it to do. Most wrong fixes come from an untested assumption about current behavior.
3. Isolate with a binary search
- Bisect over whatever axis is cheapest: commits (
git bisect), code paths (comment out / short-circuit sections), inputs (shrink the reproduction case), or layers (is it the data, the logic, or the caller?). - Narrow to the smallest unit that still reproduces the bug before forming a hypothesis about why.
4. Form one hypothesis, then test only that one
- State the specific mechanism you think is responsible, in a sentence you could be wrong about.
- Test that hypothesis directly (add an assertion, log a value, write a failing test) before changing behavior. If you change code to "see if it helps," you've stopped debugging and started guessing.
- If the hypothesis is wrong, discard the change completely and form the next one — don't leave it in "just in case."
5. Fix the root cause, not the symptom
- Prefer the fix that makes the invalid state impossible over the one that catches it after the fact (validation at the boundary vs. a null check sprinkled at every call site).
- If the real fix is large, it's fine to ship a narrow guard as a stopgap — but say so explicitly rather than presenting it as the root-cause fix.
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.
- 2mo ago First seen · 47 lines · 64 tokens per session scan A ee670d31a588
systematic-debugging is a skill published in the GitHub repository this-is-tobi/tools (5 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 737 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
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.
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…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.
diagnosing-missing-recordings
Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling…