debugging

A step-by-step method for finding the underlying cause of software bugs. It starts by reproducing the problem and examining evidence such as error messages, logs, stack traces, and user actions.

In plain words
What is it for?
Use it for bugs, failed or flaky tests, slow behaviour, production errors, and failures between connected parts of an application.
Why use it?
It reduces guesswork and prevents fixes that hide the visible symptom while leaving the real problem in place. It also helps make intermittent failures easier to investigate.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/krzysztofsurdy/code-virtuoso/debugging
Any agent
npx skills add krzysztofsurdy/code-virtuoso --skill debugging
Clone the repo
git clone --depth 1 https://github.com/krzysztofsurdy/code-virtuoso

Made for: Claude Code, Codex.

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,429 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00083 $0.02429
Opus 5 $0.00042 $0.01215
Sonnet 5 $0.00017 $0.00486
Haiku 4.5 $0.00008 $0.00243

Measured 3d ago against content hash 8a57b6ad6faf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

skills/knowledge/debugging/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugging

Systematic methodology for finding and fixing bugs. Prioritizes root cause analysis over symptom treatment, evidence over intuition, and prevention over recurrence.

Iron Law

No fix without root cause. Never apply a fix until you can explain WHY the bug exists, not just WHERE it manifests. Symptom-level fixes create new bugs.

When to Use

  • Bug report from QA or production alert
  • Test failure with unclear cause
  • Intermittent/flaky behavior
  • Performance degradation
  • Unexpected behavior that "used to work"
  • Integration failures between components

Workflow

Phase 1: Reproduce

Establish a reliable reproduction before investigating.

  1. Collect all evidence — error messages, stack traces, logs, screenshots, user steps
  2. Identify the exact conditions: environment, data state, user actions, timing
  3. Create a minimal reproduction — strip away everything that isn't needed to trigger the bug
  4. Confirm reproduction is consistent (if intermittent, note frequency and conditions)
  5. Write down the reproduction steps precisely — someone else should be able to follow them

Output: Documented reproduction steps, minimal test case

If you cannot reproduce: Document what you tried, check environment differences, add instrumentation and wait for next occurrence. Do not proceed to Phase 2 on guesswork — unreproducible bugs get logged, not "fixed."

Phase 2: Investigate

Gather evidence systematically. Do NOT form hypotheses yet — this phase is about observation, not explanation.

  1. Read the full error message and stack trace — every line, not just the first one
  2. Check git history — what changed recently? (git log --since="2 weeks ago", git bisect)
  3. Trace the data flow — follow the input from entry point to failure point
  4. Check boundaries — where does data cross component/service/layer boundaries?
  5. Collect environmental context — versions, configuration, dependencies, resource state
  6. Map the blast radius — what else is affected? Is this an isolated failure or systemic?

Read the full file on GitHub · 244 lines

Files

What ships with it

2 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.

Changes

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.

  1. 3d ago First seen · 244 lines · 83 tokens per session scan A 8a57b6ad6faf

Subscribe to this mod's changes

debugging is a skill published in the GitHub repository krzysztofsurdy/code-virtuoso (20 stars, last pushed 3mo ago), licensed MIT. It adds 83 tokens to every session and 2,429 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

cross-browser-typography-qa

Use this skill when web text looks clipped, flattened, wrapped incorrectly, misaligned, or materially different between Chromium and WebKit/Safari. Treat text rendering as both a geometry problem and a visual paint problem: passing DOM bounds does not prove that every glyph is intact.

AtlasOmnia/hermes-custom-pack · 56 tokens

hermes-agent-skill-authoring

There are two places a SKILL.md can live.

AtlasOmnia/hermes-custom-pack · 31 tokens

hermes-diagnostic-review

Use when running a read-only diagnostic review of recent Hermes sessions to find recurring mistakes, failed tool calls, and repeated fixes, then propose suggestion-only improvements and reusable skills. Human-gated; never auto-applies.

AtlasOmnia/hermes-custom-pack · 49 tokens

meta-business-posting

Publish posts to a Facebook Page using the user's own account. Two paths: the browser session (primary — works for everyone) and the Graph API (power users with a Meta app).

AtlasOmnia/hermes-custom-pack · 42 tokens

ralph-loop-template

Generate an iterable checklist PROMPT file for Ralph Loop from a plan file or the current conversation, and output the ready-to-run /ralph-loop command.

2ykwang/agent-skills · 36 tokens

code-history

Trace the git history of specific code — when a function, pattern, or file was added, modified, or removed, and the intent behind each change. Use when the user asks when or why a piece of code changed, wants the evolution of a function, or needs the commit or PR that introduced a behavior. Read-only; not for plain…

2ykwang/agent-skills · 82 tokens