What is systematic-debugging?

A step-by-step method for finding the root cause of bugs, incidents, and unclear test failures. It moves from reproducing and isolating the problem to testing a hypothesis, fixing it, and verifying the result.

Investigating failing tests, unexpected behavior, and production incidents in a consistent order.

It reduces guesswork and helps prevent fixes that only hide the symptom while leaving the underlying problem.

systematic-debugging — Skill by furkangonel

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/furkangonel/cowrangler/systematic-debugging

Any agent

npx skills add furkangonel/cowrangler --skill systematic-debugging

Clone the repo

git clone --depth 1 https://github.com/furkangonel/cowrangler

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,529 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.00014	$0.02529
Opus 5	$0.00007	$0.01264
Sonnet 5	$0.00003	$0.00506
Haiku 4.5	$0.00001	$0.00253

Measured 3d ago against content hash ca35e2937ae8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

systematic-debugging scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -v -X POST http://localhost:3000/api/orders \

bundled_skills/software-development/systematic-debugging/SKILL.md · 359 lines

How it starts

The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Systematic Debugging SOP

A methodical process for diagnosing bugs, production incidents, and unexpected behavior — without random guessing.

When to Use

User has a bug with unexpected behavior to diagnose
User has a production incident or error to investigate
User has a test that is failing for an unclear reason
User is spending more than 15 minutes on a bug without a clear hypothesis
User says "I have no idea why this is happening"

The Debugging Process

1. REPRODUCE  →  2. ISOLATE  →  3. HYPOTHESIZE  →  4. TEST  →  5. FIX  →  6. VERIFY

Never skip to step 5. Fixing a symptom without a root cause always creates more bugs.

Phase 1 — Reproduce

Goal: Produce the bug on demand, reliably.

Questions to answer:

Can you make it happen every time, or is it intermittent?
What are the exact steps to trigger it?
What did you expect to happen? What actually happened?
When did it start happening? What changed around that time?
Does it happen in all environments, or only production/staging/local?

Reproduce checklist:

Run the failing code and capture the exact error message and stack trace
Note the exact input that triggers the bug
Confirm it was working before (check git log, recent deployments)
Test in the same environment where the bug appears

# Capture full error output
python app.py 2>&1 | tee bug_repro.log

# Reproduce with exact same inputs
curl -v -X POST http://localhost:3000/api/orders \
  -H "Content-Type: application/json" \
  -d '{"item_id": 42, "quantity": 0}' \
  2>&1 | tee repro.log

If intermittent: Add logging before the suspected failure point and wait for it to happen again. Do not proceed without a reliable reproduction path.

Phase 2 — Isolate

Goal: Narrow the failing code to the smallest possible unit.

Binary Search Debugging

Cut the problem space in half with each step:

Full system fails
  → Does the API layer fail? (yes)
    → Does it fail with all requests? (no, only POST /orders)
      → Does it fail for all users? (no, only when quantity = 0)
        → ROOT: input validation doesn't reject zero quantity

Read the full file on GitHub · 359 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.

3d ago First seen · 359 lines · 14 tokens per session scan A ca35e2937ae8

Subscribe to this mod's changes

systematic-debugging is a skill published in the GitHub repository furkangonel/cowrangler (2 stars, last pushed 4d ago), licensed MIT. It adds 14 tokens to every session and 2,529 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Debugging agent agent-skills agent-tools ai bug-fixing cli cli-agent investigation production-issues root-cause troubleshooting