systematic-debugger

systematic-debugger is a skill for Claude Code, Codex from ahmadulhoq/agentskel. It costs 46 tokens per session (508 once invoked), scanned A, original, MIT.

A debugging guide for finding the confirmed cause of a software problem. It requires reproducing the issue, testing possible explanations, and verifying the fix.

In plain words
What is it for?
Use it to investigate bugs, trace their causes through the code, compare alternative explanations, and add a test that proves the problem is fixed.
Why use it?
It prevents guess-and-check fixes and makes it less likely that an apparent fix will hide the real problem.

Skill for Claude CodeCodex

Part of the agentskel plugin — 52 skills, 2 hooks shipped together

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/ahmadulhoq/agentskel/systematic-debugger
Any agent
npx skills add ahmadulhoq/agentskel --skill systematic-debugger
Clone the repo
git clone --depth 1 https://github.com/ahmadulhoq/agentskel

Made for: Claude Code, Codex.

Or install agentskel, the plugin that ships this one along with the rest of its 52 skills, 2 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 systematic-debugger

README.md
[![agentmods](https://agentmods.dev/badge/skills/ahmadulhoq/agentskel/systematic-debugger.svg)](https://agentmods.dev/skills/ahmadulhoq/agentskel/systematic-debugger)
Your own site
<a href="https://agentmods.dev/skills/ahmadulhoq/agentskel/systematic-debugger"><img src="https://agentmods.dev/badge/skills/ahmadulhoq/agentskel/systematic-debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 508 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 $0.00046 $0.00508
Opus 5 $0.00023 $0.00254
Sonnet 5 $0.00009 $0.00102
Haiku 4.5 $0.00005 $0.00051

Measured 2d ago against content hash fa110b98f1f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

systematic-debugger 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.

.agents/skills/systematic-debugger/SKILL.md · 48 lines

What it actually says

Systematic Debugger Skill

Purpose: Stop hallucination loops. Every code change requires a verified hypothesis and a failing test first.

Prohibited Behaviors

  • Adding console.log / print / debug statements without a stated hypothesis.
  • Changing code to "see what happens."
  • Fixing code before a failing test exists.
  • Treating the first hypothesis as confirmed without ruling out alternatives.

Techniques

Technique When to use
Root Cause Tracing Follow the call stack up to the originating decision point
Defense in Depth Audit every layer: input validation → business logic → persistence
Bisect Binary-search commits or code paths to find the introduction point

Required Steps (in order)

  1. Reproduce the bug reliably. If unable, state why and stop.
  2. Hypothesize: "The bug is caused by [X] because [evidence Y]."
  3. List alternatives: at least 2 other hypotheses to rule out.
  4. Create a failing test that reproduces the bug. Run it — must fail.
  5. Isolate root cause using a technique above. Rule out alternatives explicitly.
  6. Fix with minimum code targeting the confirmed root cause only.
  7. Verify: failing test now passes; full suite has no regressions.
  8. Log: update .memory/LESSONS.md with root cause + prevention rule.

Common Rationalizations

Rationalization Why it's wrong Do this instead
"I'll just try changing X and see" That's the loop we're breaking State a hypothesis first
"The test is hard to write here" Difficulty ≠ exemption Document why and get explicit sign-off
"I'm pretty sure it's Y" Pretty sure ≠ confirmed Rule out alternatives before fixing
"I'll add a log to check" Logs without hypotheses produce noise State what you expect the log to show first

Gate: Do not change production code until step 4 (failing test) is complete and step 5 (root cause confirmed) is documented.

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 · 48 lines · 46 tokens per session scan A fa110b98f1f2

Subscribe to this mod's changes

systematic-debugger is a skill published in the GitHub repository ahmadulhoq/agentskel (13 stars, last pushed 18d ago), licensed MIT. It adds 46 tokens to every session and 508 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 2026-09-02.

Related

Other skills, from other repositories

tdd

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

GreyDGL/PentestGPT · 33 tokens

test-first-bugs

Enforces a test-driven bug-fixing workflow. Use when a user reports a bug, failing code, an error, or asks to fix something.

jamditis/claude-skills-journalism · 35 tokens

tdd

Test-driven development (TDD) process used when writing code. Use whenever you are adding any new code, unless the user explicitly asks to skip TDD or the code is exploratory/spike.

lexler/skill-factory · 42 tokens

growing-outside-in-systems

Drive feature development using Outside-In TDD with Hexagonal Architecture. Design emerges through inline code, in-memory fakes, interface extraction, and deferred I/O. Use when building features, writing tests, or structuring backend services. Triggers on: TDD, outside-in, hexagonal, ports and adapters, emergent…

lexler/skill-factory · 122 tokens

plan-create

Create structured implementation plans for autonomous TDD development. Use for new features, multi-file changes, or anything requiring multiple steps or tests. Triggers on aspirational openers ("let's build", "let's start building", "I want to make", "I want an app that", "help me build"), capability lists ("users…

markshust/hcf · 171 tokens

red-green-refactor

Guides the red-green-refactor TDD workflow: write a failing test first, implement the minimum code to make it pass, then refactor while keeping tests green. Use when a user asks to practice TDD, write tests first, follow red-green-refactor, do test-driven development, write failing tests before code, or phrases like…

rohitg00/skillkit · 90 tokens