debugging

debugging is a skill for Claude Code, Codex from WingedGuardian/GENesis-AGI. It costs 32 tokens per session (596 once invoked), scanned A, original, MIT.

A step-by-step method for finding the cause of a failed test, runtime error, or other unexpected software behavior.

In plain words
What is it for?
It is for diagnosing test failures, runtime errors, anomalous system behavior, and recurring technical issues, then recording the cause and fix.
Why use it?
It replaces guesswork with reproduction, isolation, hypothesis testing, a focused fix, and verification that the problem is gone without new regressions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

Good fit It is for diagnosing test failures, runtime errors, anomalous system behavior, and…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wingedguardian/genesis-agi/debugging
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.

Any agent
npx skills add WingedGuardian/GENesis-AGI --skill debugging
Clone the repo
git clone --depth 1 https://github.com/WingedGuardian/GENesis-AGI

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for debugging

README.md
[![agentmods](https://agentmods.dev/badge/skills/wingedguardian/genesis-agi/debugging.svg)](https://agentmods.dev/skills/wingedguardian/genesis-agi/debugging)
Your own site
<a href="https://agentmods.dev/skills/wingedguardian/genesis-agi/debugging"><img src="https://agentmods.dev/badge/skills/wingedguardian/genesis-agi/debugging.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 596 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00032 $0.00596
Opus 5 $0.00016 $0.00298
Sonnet 5 $0.00006 $0.00119
Haiku 4.5 $0.00003 $0.00060

Measured 7d ago against content hash 7cb13a286ee1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 7d 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.

src/genesis/skills/debugging/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugging

Purpose

Systematically diagnose and resolve bugs, failures, or unexpected behavior in Genesis or its dependencies.

When to Use

  • A test fails unexpectedly.
  • Runtime error or unexpected behavior is reported.
  • An awareness tick or reflection produces anomalous results.
  • Obstacle resolution escalates a technical issue.

Workflow

  1. Reproduce — Confirm the issue. Get the exact error, stack trace, or unexpected output. Define "expected vs. actual."
  2. Isolate — Narrow the scope. Which module? Which function? Which input triggers it? Use binary search on the call chain.
  3. Hypothesize — Form 2-3 candidate explanations. Rank by likelihood.
  4. Test hypotheses — Write a minimal test or add logging to confirm/deny each hypothesis. Start with the most likely.
  5. Fix — Apply the minimal correct fix. Do not fix adjacent issues in the same change.
  6. Verify — Run the failing test. Run the full test suite. Confirm no regressions.
  7. Document — Record the root cause and fix as an observation. Update procedures if the bug class is recurring.

Output Format

issue: <one-line description>
date: <YYYY-MM-DD>
root_cause: <what actually went wrong>
fix: <what was changed>
files_modified:
  - <file path>
regression_risk: low | medium | high
lesson: <what to remember to prevent recurrence>

Examples

Example: Hook fails in non-login shell

Trigger: Post-commit hook throws KeyError: 'HOME' in CI-like environment.

Expected output:

issue: Post-commit hook crashes when HOME not set in non-login sessions
date: 2026-04-06
root_cause: Hook script reads os.environ["HOME"] but non-login shells
  (systemd, cron) strip HOME from environment
fix: Guard with os.environ.get("HOME", "/root") fallback + persist HOME
  in /etc/environment during install
files_modified:
  - .claude/hooks/genesis-hook
  - scripts/install_guardian.sh
regression_risk: low
lesson: Never assume HOME exists — non-login shells strip it. Always
  use get() with fallback for environment variables in hook scripts.

Read the full file on GitHub · 79 lines

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. 7d ago First seen · 79 lines · 32 tokens per session scan A 7cb13a286ee1

Subscribe to this mod's changes

debugging is a skill published in the GitHub repository WingedGuardian/GENesis-AGI (95 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 596 once invoked, about $0.0002 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.