agentmods.dev

debug

debug is a skill for Claude Code from nicograef/handbook. It costs 35 tokens per session (318 once invoked), scanned A, original, MIT.

A debugging workflow that reproduces a failure, compares possible causes, and identifies the underlying cause before changing code.

In plain words
What is it for?
It helps investigate hard bugs, flaky tests, regressions, and unexplained command failures. It narrows flaky failures into repeatable cases and tests one possible cause at a time.
Why use it?
It prevents guesswork and fixes aimed only at where a symptom appears. It also turns the confirmed reproduction into a regression test, which checks that the bug stays fixed.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the nico plugin — 10 skills, 1 agent, 4 hooks shipped together

not rated 2repo changed yesterday A scan 35 tokens original MIT

Good fit It helps investigate hard bugs, flaky tests, regressions, and unexplained command failures. It narrows flaky failures into repeatable cases and tests one possible cause at a time.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nicograef/handbook/debug
View source ↗ nicograef/handbook
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 nicograef/handbook --skill debug
Clone the repo
git clone --depth 1 https://github.com/nicograef/handbook

Made for: Claude Code.

Or install nico, the plugin that ships this one along with the rest of its 10 skills, 1 agent, 4 hooks.

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 debug

README.md
[![agentmods](https://agentmods.dev/badge/skills/nicograef/handbook/debug/github.svg)](https://agentmods.dev/skills/nicograef/handbook/debug)
Your own site
<a href="https://agentmods.dev/skills/nicograef/handbook/debug"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/debug/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.

agentmods 80×15 button for debug

Your own site · 80×15
<a href="https://agentmods.dev/skills/nicograef/handbook/debug"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 318 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 $0.00035 $0.00318
Opus 5.5 $0.00014 $0.00127
Sonnet 5.5 $0.00007 $0.00064
Haiku 4.5 $0.00003 $0.00032

Measured yesterday against content hash e04d82148805, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

debug 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 yesterday.

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.

plugin/skills/debug/SKILL.md · 28 lines

What it actually says

Debug

Arguments: $ARGUMENTS: the symptom, a failing command or a pasted error.

Gotchas

  • No fix before a repro. A fix that was never red proves nothing.
  • Temporary debug output carries one unique prefix, such as DBG-<slug>:. Grep it out before committing.

Loop

  1. Build one fast, deterministic command that shows the exact symptom and can go red. A flaky bug gets a seed, a loop count or a pinned clock until it fails on demand.
  2. Shrink the repro: drop input, steps and dependencies while it stays red.
  3. Rank 3–5 falsifiable hypotheses by likelihood and cost to test. Each names the observation that would refute it.
  4. Test one hypothesis with one change at a time. Revert a change that refuted its hypothesis.
  5. Name the root cause, then fix it there, not where the symptom surfaced.
  6. Keep the repro as a regression test only under the global test rule. Otherwise the red-green run is the proof and the repro is deleted.

No seam

A bug no test can reach without a running system is an architecture finding. Report it with the repro command and the missing seam.

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. yesterday Changed · -1 lines e04d82148805
  2. 12d ago Changed e092ee5f9f3d
  3. 16d ago First seen · 29 lines · 35 tokens per session scan A 49378d7d8599

Subscribe to this mod's changes

debug is a skill published in the GitHub repository nicograef/handbook (2 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 318 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 2026-10-21.

DebuggingTestingUnit testing
Related

debug compared with skills from other repositories

debug next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
debugnicograef/handbookSkill22d agoMITA35Claude Code
gstack-investigategarrytan/gstackSkill140kyesterdayMITA40Claude Code, Codex
testinggarrytan/gbrainSkill32kyesterdayMITA63Claude Code
verifyYeachan-Heo/oh-my-claudecodeSkill41kyesterdayMITA12Claude Code
detect-static-dependenciesdotnet/skillsSkill5.8kyesterdayMITA135Claude Code
testing-blocksadobe/skillsSkill319yesterdayApache-2.0A61Claude Code
dart-downstream-fixdartsim/dartSkill1.2kyesterdayBSD-2-ClauseA25Claude Code