debug-triage

debug-triage is a skill for Claude Code from Sagargupta16/claude-skills. It costs 61 tokens per session (584 once invoked), scanned A, original, MIT.

A debugging guide for reading pasted errors, stack traces, and terminal logs to identify the likely cause and explain how to fix it.

In plain words
What is it for?
Use it to diagnose runtime errors, trace failures through a stack trace, suggest a code change or shell command, name a regression test, and note any documentation that also needs updating.
Why use it?
It turns a long or confusing error report into a short cause, fix, and test plan. It helps separate the underlying problem from the first visible symptom.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the debug-triage plugin — 1 skill shipped together

Good fit Use it to diagnose runtime errors, trace failures through a stack trace, suggest a code change or shell command, name a regression test, and note any documentation that also needs updating.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sagargupta16/claude-skills/debug-triage
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 Sagargupta16/claude-skills --skill debug-triage
Clone the repo
git clone --depth 1 https://github.com/Sagargupta16/claude-skills

Made for: Claude Code.

Or install debug-triage, the plugin that ships this one along with the rest of its 1 skill.

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-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/sagargupta16/claude-skills/debug-triage/github.svg)](https://agentmods.dev/skills/sagargupta16/claude-skills/debug-triage)
Your own site
<a href="https://agentmods.dev/skills/sagargupta16/claude-skills/debug-triage"><img src="https://agentmods.dev/badge/skills/sagargupta16/claude-skills/debug-triage/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-triage

Your own site · 80×15
<a href="https://agentmods.dev/skills/sagargupta16/claude-skills/debug-triage"><img src="https://agentmods.dev/badge/skills/sagargupta16/claude-skills/debug-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 584 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 $0.00061 $0.00584
Opus 5 $0.00030 $0.00292
Sonnet 5 $0.00012 $0.00117
Haiku 4.5 $0.00006 $0.00058

Measured 10d ago against content hash 948ff639093d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

debug-triage 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 10d 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.

plugins/debug-triage/skills/debug-triage/SKILL.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

debug-triage

When to activate

  • User pastes a terminal or PowerShell transcript containing an error.
  • User pastes a stack trace.
  • User says "debug", "fix this", "why is this broken", "what's going on here".

Do NOT activate for refactoring requests, feature work, or general code review -- those are separate tasks.

Steps

  1. Parse the actual error. Read stack traces bottom-up. The top frame is usually the symptom; the root cause is deeper in the stack or earlier in the log. Ignore generic first lines like "Traceback (most recent call last):" or "Uncaught Error".
  2. State the likely cause in one sentence. Not a paragraph. "Null dereference on user.profile because the auth middleware returns null for unverified emails."
  3. Propose the fix as a diff or command. Not prose. Either a code snippet showing before/after, or the exact shell command to run.
  4. Name a regression test. Where it would live (tests/auth/email_verify_test.py), and what assertion would catch this bug next time. One line.
  5. Flag sibling updates. If the fix changes behavior documented in README, CHANGELOG, or any doc file, list them. If not, say "none".

Rules

  • Don't ask the user to reformat the paste. Parse whatever they gave you.
  • Fix first, explain if asked. Don't narrate what the error means at length.
  • Ambiguous errors: if 2+ causes are equally likely, pick the likeliest and say so in one line. Do not dump all possibilities unless asked.
  • Recent changes are suspect. Run git log -5 --oneline -- <file> on the failing file. If a recent commit touched the failing line, mention it.
  • Environment first. If the error looks like it could be environmental (missing env var, wrong Node/Python version, CRLF line endings, path with spaces), check the environment before hypothesizing code bugs.

Output

Cause: <one line>
Fix: <diff or command>
Regression test: <path + what it asserts>
Siblings to update: <list or "none">

No preamble. Lead with Cause:.

Read the full file on GitHub · 43 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. 10d ago First seen · 43 lines · 61 tokens per session scan A 948ff639093d

Subscribe to this mod's changes

debug-triage is a skill published in the GitHub repository Sagargupta16/claude-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 61 tokens to every session and 584 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Systematic debugging approach for errors, test failures, and unexpected behavior. Use when encountering bugs, test failures, errors, or when debugging is needed. Prevents common anti-patterns like random fixes, skipping root cause analysis, and thrashing.

shrwnsan/vibekit-claude-plugins · 54 tokens

crashlytics

Generate crash reports from Firebase Crashlytics with automated fix proposals, severity scoring, and developer assignments via git blame. Use when analyzing crashes, triaging production issues, or generating crash triage reports.

artemnovichkov/skills · 45 tokens

audit-dead-code

Hunt dead code across a whole repository through four labelled lanes of unequal confidence. Knip (TS/JS unused files, exports, types, enum members), vulture (Python symbols), gopls (Go unexported symbols), and a portable grep lane (shell and other symbol languages), then adjudicate every candidate against the…

melodic-software/claude-code-plugins · 254 tokens

doctor

Check ryk installation, policy status, host integration status, and plugin readiness.

christopherkarani/ryk · 0 tokens

ci-log-interpretation

Use this skill when reading or analyzing CI logs from a Shopware GitHub Actions workflow to figure out why a build failed — phrases like "why did CI fail", "what broke the build", "check the pipeline", "interpret these logs", "debug this red build" — or whenever raw run logs, job logs, or check annotations from a…

shopwareLabs/ai-coding-tools · 154 tokens

ryk-doctor

Check ryk installation, policy status, host integration status, and plugin readiness.

christopherkarani/ryk · 0 tokens