agentmods.dev

systematic-debugging

systematic-debugging is a skill for Claude Code, Codex from tolgakisaogullari/SumelaOS. It costs 23 tokens per session (726 once invoked), scanned A, original, MIT.

A step-by-step method for investigating bugs, failed tests, and unexpected software behavior before changing code. It traces the problem to its cause, compares working examples, tests one hypothesis, and verifies the result.

In plain words
What is it for?
Use it to reproduce failures, inspect error details, trace incorrect data, compare similar code, create focused tests, and verify fixes.
Why use it?
It helps prevent guesswork and bundled changes that make it difficult to know which change fixed or caused a problem.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 4repo 13d ago A scan 23 tokens original MIT

Good fit Use it to reproduce failures, inspect error details, trace incorrect data, compare similar code, create focused tests, and verify fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tolgakisaogullari/sumelaos/systematic-debugging
View source ↗ tolgakisaogullari/SumelaOS
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 tolgakisaogullari/SumelaOS --skill systematic-debugging
Clone the repo
git clone --depth 1 https://github.com/tolgakisaogullari/SumelaOS

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 systematic-debugging

README.md
[![agentmods](https://agentmods.dev/badge/skills/tolgakisaogullari/sumelaos/systematic-debugging.svg)](https://agentmods.dev/skills/tolgakisaogullari/sumelaos/systematic-debugging)
Your own site
<a href="https://agentmods.dev/skills/tolgakisaogullari/sumelaos/systematic-debugging"><img src="https://agentmods.dev/badge/skills/tolgakisaogullari/sumelaos/systematic-debugging.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 726 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 $0.00023 $0.00726
Opus 5 $0.00012 $0.00363
Sonnet 5 $0.00005 $0.00145
Haiku 4.5 $0.00002 $0.00073

Measured 8d ago against content hash 78b64d144a9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

systematic-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 8d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (find-polluter.cmd, find-polluter.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.sumela/skills/systematic-debugging/SKILL.md · 53 lines

What it actually says

<debugging_workflow> Execute these 4 phases sequentially:

  1. ROOT CAUSE INVESTIGATION:

    • SECOND BRAIN CHECK: Before deep-diving, scan wiki/tech-debt-and-known-issues.md for related TD entries — the bug may already be documented as known debt. Also check wiki/architecture-decisions.md for constraints that may explain the behavior. This prevents re-discovering problems the wiki already tracks.
    • Read full error messages and stack traces.
    • Reproduce the issue consistently in the current state.
    • For multi-layer systems: Add diagnostic logs at component boundaries to isolate the failing layer.
    • Trace data flow backward to find where the bad value originated (see ./root-cause-tracing.md).

  2. PATTERN ANALYSIS:

    • Find similar working code in the codebase as a reference.
    • Identify exact differences between the working reference and the broken code.

  3. HYPOTHESIS & ISOLATION:

    • Formulate a single, specific hypothesis.
    • Make the SMALLEST possible isolated change to test it. Do not bundle multiple fixes.

  4. IMPLEMENTATION & VERIFICATION (ADAPTIVE TDD & STAGED WORKFLOW):

    • Check the TDD Mode.
      • IF Enabled: Create a failing test case first that reproduces the issue.
      • IF Skipped: Proceed to fix directly, UNLESS the bug involves AuthN, AuthZ, or security boundaries. Security bugs ALWAYS require a failing test to prove the vulnerability before fixing.
    • Implement the single fix. You MUST ensure the fix strictly adheres to the secure-coding-standard. Never bypass security layers (e.g., wildcards, disabling auth) just to make a bug disappear.
    • MANDATORY: Invoke the verification-before-completion skill to strictly verify the fix works and no regressions occurred.
    • Once verified, ONLY stage the fixed files (git add <files>). DO NOT use git commit.
    • Inform the orchestrator/user that the fix is STAGED and ready for the requesting-code-review skill. </debugging_workflow>

<architectural_escalation> CRITICAL RULE: If your fix does not work, REVERT IT safely before trying another. Do not pile fixes on top of failed fixes.

  • SAFE REVERT: Use git restore <file> or git checkout -- <file> to discard unstaged failed attempts. NEVER use git reset --hard as it will destroy other successfully staged work.

If you attempt 3 separate isolated fixes and ALL fail:

  • STOP IMMEDIATELY. Do not attempt a 4th fix.
  • Revert your last failed attempt to keep the working tree clean.
  • This is an architectural problem, not a simple bug.
  • Escalate to the human partner to rethink the fundamental architecture or pattern. </architectural_escalation>

<supporting_techniques> Reference these if applicable:

  • ./defense-in-depth.md (Add validation at multiple layers)
  • ./condition-based-waiting.md (Replace arbitrary timeouts with condition polling) </supporting_techniques>
Files

What ships with it

5 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. 8d ago First seen · 53 lines · 23 tokens per session scan A 78b64d144a9d

Subscribe to this mod's changes

systematic-debugging is a skill published in the GitHub repository tolgakisaogullari/SumelaOS (4 stars, last pushed 13d ago), licensed MIT. It adds 23 tokens to every session and 726 once invoked, about $0.0001 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.

Debugging
Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens