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 dork-labs/dorkos --skill debugging-systematicallygit clone --depth 1 https://github.com/dork-labs/dorkosWrote 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/dork-labs/dorkos/debugging-systematically)<a href="https://agentmods.dev/skills/dork-labs/dorkos/debugging-systematically"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/debugging-systematically/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/dork-labs/dorkos/debugging-systematically"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/debugging-systematically.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00027 | $0.02462 |
| Opus 5.5 | $0.00011 | $0.00985 |
| Sonnet 5.5 | $0.00005 | $0.00492 |
| Haiku 4.5 | $0.00003 | $0.00246 |
Grade A, and why
debugging-systematically 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 28d 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 — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugging Systematically
This skill provides debugging methodology — systematic approaches to finding and fixing bugs. It covers the mental models and techniques for effective troubleshooting.
For specific debugging tools: See /debug:* commands.
Core Debugging Methodology
The Scientific Method for Bugs
- Observe — What is actually happening?
- Hypothesize — What could cause this?
- Test — Design an experiment to verify
- Analyze — Did the test confirm or refute?
- Iterate — Refine hypothesis and repeat
The Golden Rule
Understand before you fix.
Never make changes to code you don't understand. Reading and comprehending the code often reveals the bug.
Problem Articulation
Questions to Answer First
| Question | Why It Matters |
|---|---|
| What should happen? | Defines the expected behavior |
| What actually happens? | Identifies the discrepancy |
| When did it start? | Narrows the scope of changes |
| What changed recently? | Identifies potential causes |
| Is it reproducible? | Determines debugging approach |
Rubber Duck Method
The act of explaining code line-by-line forces you to:
- Think through logic sequentially
- Surface implicit assumptions
- Notice gaps in understanding
- Catch inconsistencies
Often, the solution becomes obvious mid-explanation.
Hypothesis Formation
Common Bug Categories
| Category | Symptoms | Check |
|---|---|---|
| Data | Wrong values, undefined | Log actual values |
| Logic | Wrong branch, off-by-one | Trace conditionals |
| Timing | Race conditions, stale data | Check async flow |
| State | Inconsistent behavior | Inspect state at each step |
| Integration | API mismatches | Verify contracts |
What ships with it
4 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.
- 28d ago Changed 50a1d5016c4c
- 2mo ago First seen · 349 lines · 27 tokens per session scan A d9f1e7246119
debugging-systematically is a skill published in the GitHub repository dork-labs/dorkos (11 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 2,462 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 2026-08-31.
debugging-systematically compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| debugging-systematicallydork-labs/dorkos | Skill | 11 | today | MIT | A | 27 | Claude Code |
| browser-edge-casesaden-hive/hive | Skill | 11k | 2d ago | Apache-2.0 | A | 40 | Claude Code |
| triage-issueaden-hive/hive | Skill | 11k | 2d ago | Apache-2.0 | A | 0 | Claude Code |
| hive.error-recoveryaden-hive/hive | Skill | 11k | 2d ago | Apache-2.0 | A | 25 | Claude Code, Codex |
| hive.terminal-tools-troubleshootingaden-hive/hive | Skill | 11k | 2d ago | Apache-2.0 | C | 85 | Claude Code, Codex |
| concurrency-and-asynctmj-90/gaffer | Skill | 1 | yesterday | Apache-2.0 | A | 108 | Claude Code, Codex |
| concurrency-reviewtmj-90/gaffer | Skill | 1 | yesterday | Apache-2.0 | A | 131 | Claude Code, Codex |