debugging

A step-by-step process for finding and fixing software bugs, including errors reported by Sentry, a service that tracks application failures. It covers investigation, reproduction, correction, testing, and preparing a code change.

In plain words
What is it for?
Use it to handle bug reports, production errors, Sentry issues, and regressions—problems where previously working behavior has broken. It helps create a failing test, apply a focused fix, verify the result, and prepare a pull request.
Why use it?
It gives developers a consistent way to trace a problem to its root cause and avoid unrelated changes. It also checks that a test fails for the real bug and passes after the fix.

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/deepank308/hermes-swe-agent/debugging
Any agent
npx skills add Deepank308/hermes-swe-agent --skill debugging
Clone the repo
git clone --depth 1 https://github.com/Deepank308/hermes-swe-agent

Made for: Claude Code, Codex.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 546 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 $0.00035 $0.00546
Opus 5 $0.00017 $0.00273
Sonnet 5 $0.00007 $0.00109
Haiku 4.5 $0.00003 $0.00055

Measured 2d ago against content hash 76d7ed3ee946, 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 2d 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/debugging/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugging Workflow

Use this workflow for bug reports, production errors, Sentry issues, and regressions.

Phase 1: Investigate

  1. Read the ticket for error details, stack traces, Sentry links, and reproduction steps.
  2. If a Sentry URL is provided: invoke /debugging-sentry-issues for Sentry/Metabase MCP investigation.
  3. If local debugging is needed: invoke /debug-reference for Docker environment commands and debugging tips.
  4. Invoke superpowers:systematic-debugging and follow its 4-phase methodology:
    • Root cause analysis: trace the error to its origin.
    • Pattern analysis: identify what conditions trigger the bug.
    • Hypothesis formation: form a testable theory about the cause.
    • Implementation: plan the minimal fix.

Phase 2: Reproduce

  1. Create a failing test that captures the bug scenario.
  2. Run the test and verify it fails for the right reason (the actual bug, not a setup issue).
  3. This serves as the TDD RED phase — the test defines the expected correct behavior.

Phase 3: Fix

  1. Implement a minimal, targeted fix — only address the root cause.
  2. Do not refactor surrounding code or fix unrelated issues.
  3. Run the failing test and verify it now passes (TDD GREEN phase).

Phase 4: Verify

Invoke superpowers:verification-before-completion and follow its methodology:

  • Run the broader test suite to check for regressions.
  • Run lint on changed JS/TS files.
  • If any failures: fix the issue and re-verify (up to 3 attempts).
  • Do NOT proceed to Phase 5 until all checks pass with evidence.

Phase 5: Commit & PR

  1. Stage changed files and commit with a Fix: <description> message.
  2. Push to the working branch.
  3. Create a PR with:
    • Title. Include Linear Issue identifier ([ENG-XXXX]: Fix <concise description>).
    • Description including:
      • Root cause analysis.
      • What the fix does and why.
      • Test results.

Phase 6: Summary

Output a summary:

  • Root cause of the bug.
  • How it was reproduced (test name/description).
  • What the fix does.
  • Test results (pass counts, no regressions).
  • PR link.

Read the full file on GitHub · 62 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. 2d ago First seen · 62 lines · 35 tokens per session scan A 76d7ed3ee946

Subscribe to this mod's changes

debugging is a skill published in the GitHub repository Deepank308/hermes-swe-agent (11 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 546 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens