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 humanerd-drew/opencode-drewgent --skill systematic-debugginggit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWrote 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/humanerd-drew/opencode-drewgent/systematic-debugging)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/systematic-debugging"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/systematic-debugging.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.13476 |
| Opus 5 | $0.00019 | $0.06738 |
| Sonnet 5 | $0.00008 | $0.02695 |
| Haiku 4.5 | $0.00004 | $0.01348 |
Grade C, and why
systematic-debugging scanned grade C with 2 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Destructive operations (`rm -rf`, `docker compose down`, `drop database`, `kubectl delete`) can cause data loss, service outage, or cascade failures the agent cannot recover from Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- A curl test from your terminal is the same environment as `wrangler dev`. A deployed Worker is NOT. How it starts
The opening of the file, as written. The whole thing — 1,351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
Overview
Core principle: ALWAYS find root cause before attempting fixes. Symptom fixes are failure.
Preceding principle — Phase 0: NEVER assume system architecture from naming conventions. Verify the actual wiring (base URL, provider registration, API key env vars) before making claims about how a provider/model/service routes. See the Phase 0 section below.
Violating the letter of this process is violating the spirit of debugging.
The Iron Law
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
If you haven't completed Phase 1, you cannot propose fixes.
When to Use
Use for ANY technical issue:
- Test failures
- Bugs in production
- Unexpected behavior
- Performance problems
- Build failures
- Integration issues
Use this ESPECIALLY when:
- Under time pressure (emergencies make guessing tempting)
- "Just one quick fix" seems obvious
- You've already tried multiple fixes
- Previous fix didn't work
- You don't fully understand the issue
Don't skip when:
- Issue seems simple (simple bugs have root causes too)
- You're in a hurry (rushing guarantees rework)
- Someone wants it fixed NOW (systematic is faster than thrashing)
First-Fix Rule: Cross-File Audit Before Any Fix
WHEN you encounter ANY error in a recently-refactored or extracted codebase:
- Do NOT attempt a single fix.
- Immediately run a comprehensive cross-file audit to find ALL broken references.
- Fix them ALL in one batch.
Why: Refactoring extractions ALWAYS leave multiple dangling references across multiple files. Each "fix one → discover next" cycle wastes turns and frustrates the user.
User signal to trigger this: If the user says anything like "하나씩 문제가 달라지는데, 전수조사 좀 해봐라" (problems keep changing one at a time, do a thorough investigation) — or even BEFORE they say it, the FIRST time a second distinct error appears after a fix — switch to comprehensive audit mode IMMEDIATELY.
The audit must cover:
- All files modified in the extraction (
git diff --name-only) - All functions from the original module referenced in extracted files
- All lazy imports needed (circular dependency check)
- All call sites that need updating (
self.method()→function(self, ...)) - All registration points (class attribute assignment)
- All leftover debris at file ends
- All cached
.pycfiles that mask errors
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 1,351 lines · 0 tokens per session scan C aa764517767e
systematic-debugging is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 13,476 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
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.