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 agentmods add skills/developersglobal/ai-agent-skills/debugging-methodologynpx skills add DevelopersGlobal/ai-agent-skills --skill debugging-methodologygit clone --depth 1 https://github.com/DevelopersGlobal/ai-agent-skillsWhat 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 | $0.00026 | $0.00942 |
| Opus 5 | $0.00013 | $0.00471 |
| Sonnet 5 | $0.00005 | $0.00188 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
debugging-methodology 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 3d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Random code changes in response to errors are not debugging — they're noise generation. This skill enforces a systematic, hypothesis-driven approach: understand the problem, form a hypothesis, test it, confirm the root cause, then fix.
AI agents often cycle through random fixes until something "works." This skill prevents that.
When to Use
- Any time a test fails unexpectedly
- Any time you encounter an error or exception
- When behavior differs between environments
- When performance degrades unexpectedly
Process
Step 1: Reproduce Reliably
- Before doing anything else: reproduce the bug reliably. If you can't reproduce it, you can't fix it.
- Write a failing test that captures the bug — this becomes your regression test.
- Note the exact conditions that trigger the bug: inputs, environment, sequence of actions.
Verify: You can trigger the bug on demand.
Step 2: Understand Before Diagnosing
- Read the full error message — not just the first line.
- Read the stack trace from bottom to top — the root cause is usually near the bottom.
- Identify: What was the program trying to do? What happened instead?
Verify: You can explain the bug in one sentence without using the word "error."
Step 3: Form a Hypothesis
- Based on what you know, form a specific hypothesis: "I think the bug is X because Y."
- The hypothesis must be falsifiable — you can design a test that proves or disproves it.
- Do not start making code changes until you have a hypothesis.
Verify: Your hypothesis is specific enough to design a test for.
Step 4: Test the Hypothesis
- Add targeted logging or a targeted test that confirms or refutes the hypothesis.
- Run it. Read the output carefully.
- If the hypothesis is wrong: update your understanding, form a new hypothesis, repeat.
- If the hypothesis is right: you've found the root cause.
Verify: Root cause is confirmed by evidence, not assumed.
Step 5: Fix the Root Cause (Not the Symptom)
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.
- 3d ago First seen · 102 lines · 26 tokens per session scan A 1e001991f84c
debugging-methodology is a skill published in the GitHub repository DevelopersGlobal/ai-agent-skills (65 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 942 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
code-review-and-quality
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
constraint-driven-development
Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-ignore or…
performance-optimization
Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.
api-and-interface-design
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
code-simplification
Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now…