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 yimwoo/hotl-plugin --skill systematic-debugginggit clone --depth 1 https://github.com/yimwoo/hotl-pluginWrote 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/yimwoo/hotl-plugin/systematic-debugging)<a href="https://agentmods.dev/skills/yimwoo/hotl-plugin/systematic-debugging"><img src="https://agentmods.dev/badge/skills/yimwoo/hotl-plugin/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/yimwoo/hotl-plugin/systematic-debugging"><img src="https://agentmods.dev/badge/skills/yimwoo/hotl-plugin/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 | $0.00022 | $0.00230 |
| Opus 5.5 | $0.00009 | $0.00092 |
| Sonnet 5.5 | $0.00004 | $0.00046 |
| Haiku 4.5 | $0.00002 | $0.00023 |
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 1mo 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.
What it actually says
Systematic Debugging
Four Phases
Phase 1: Reproduce
- Get a minimal, reliable reproduction
- Never fix what you can't reproduce
Phase 2: Understand
- Read the error message fully — the answer is often there
- Trace the call path from symptom to root cause
- Check: recent changes, environment differences, assumptions about inputs
Phase 3: Hypothesize
- Form 1-3 specific hypotheses about root cause
- Test each hypothesis with the smallest possible change
- Never change multiple things at once
Phase 4: Fix and Verify
- Fix the root cause, not the symptom
- Run the reproduction case — confirm fixed
- Run full test suite — confirm no regressions
- Invoke
hotl:verification-before-completion
Red Flags
- "Let me try X and see what happens" without a hypothesis
- Changing multiple things before verifying
- Marking done without running full tests
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.
- 1mo ago First seen · 35 lines · 22 tokens per session scan A cb5421eab794
systematic-debugging is a skill published in the GitHub repository yimwoo/hotl-plugin (27 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 230 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 2026-08-30.
Other skills, from other repositories
probe-first-scout
Use when the real uncertainty is operational and a full implementation plan would be fake confidence. Design and run the smallest probe that can surface the real red light, define the expected green light, and package the result for the planning layer.
performance-review
Review measurable frontend and backend performance risks including bundles, rendering, network, caching, images, queries, latency, memory, and polling.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
anti-entropy-governance
Use when touching retiring old logic, collapsing duplicate owners, removing fallbacks, or schema/persistence/source-of-truth boundaries; identify opportunities automatically; destructive execution requires explicit confirmation.
systematic-debugging
4-phase root cause analysis: observe, hypothesize, verify, fix. Enforces investigation before any code changes. Emergency stop after 2 failed fixes. Prevents shotgun debugging and fix cascades.
om-troubleshooter
Diagnose and fix standalone Open Mercato bugs across scope, commands, locking, fields, generated registries, UI hydration, cache/search, bootstraps, queues, and providers. Use for "fix bug", "why does this fail", "regression", "debug", "napraw błąd", or a failing test.