systematic-debugging

systematic-debugging is a skill for Claude Code, Codex from itallstartedwithaidea/agent-skills. It costs 24 tokens per session (1,353 once invoked), scanned A, original, MIT.

A four-phase method for finding the underlying cause of a software bug: reproduce it, rank possible causes, test them with small measurements, and apply a targeted fix.

In plain words
What is it for?
It helps investigate failing or intermittent tests, stack traces, user-reported bugs, and problems that appear after recent changes.
Why use it?
It replaces changing several things at once with evidence-based investigation, making it clearer why the bug occurred and whether the fix works.

Skill for Claude CodeCodex

Part of the software-dev-skills plugin — 8 skills shipped together , and of all-skills

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

Made for: Claude Code, Codex.

Or install software-dev-skills, the plugin that ships this one along with the rest of its 8 skills.

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/itallstartedwithaidea/agent-skills/systematic-debugging.svg)](https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/systematic-debugging)
Your own site
<a href="https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/systematic-debugging"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/systematic-debugging.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,353 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 $0.00024 $0.01353
Opus 5 $0.00012 $0.00677
Sonnet 5 $0.00005 $0.00271
Haiku 4.5 $0.00002 $0.00135

Measured yesterday against content hash b26f5b5c4f17, 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 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 yesterday.

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/software-dev/systematic-debugging/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Systematic Debugging

Part of Agent Skills™ by googleadsagent.ai™

Description

Systematic Debugging replaces trial-and-error fixes with a disciplined four-phase root cause analysis process. The agent reproduces the bug reliably, generates ranked hypotheses, tests each hypothesis with minimal instrumentation, and applies a targeted fix with defense-in-depth hardening. No fix is applied without first understanding why the bug exists.

Agents are prone to "shotgun debugging"—changing multiple things simultaneously and hoping the problem disappears. This skill enforces scientific rigor: one variable at a time, observable evidence at each step, and a clear causal chain from root cause to fix. The agent must articulate the root cause in plain language before writing any corrective code.

After the immediate fix, the agent applies defense-in-depth: adding assertions, input validation, or monitoring that would catch the same class of bug in the future. The debugging session concludes with a post-mortem note documenting the root cause, the fix, and the preventive measures added.

Use When

  • A test fails unexpectedly or intermittently
  • A user reports a bug with a stack trace or reproduction steps
  • Code behaves differently in production than in development
  • An error message is unclear or misleading
  • Multiple potential causes exist and guessing would waste time
  • A previous fix attempt did not resolve the issue

How It Works

graph TD
    A[Bug Report] --> B[Phase 1: Reproduce]
    B --> C{Reproducible?}
    C -->|No| D[Gather More Context]
    D --> B
    C -->|Yes| E[Phase 2: Hypothesize]
    E --> F[Rank Hypotheses by Likelihood]
    F --> G[Phase 3: Test Top Hypothesis]
    G --> H{Root Cause Found?}
    H -->|No| I[Eliminate Hypothesis]
    I --> F
    H -->|Yes| J[Phase 4: Fix + Harden]
    J --> K[Write Regression Test]
    K --> L[Apply Defense-in-Depth]
    L --> M[Document Post-Mortem]

Read the full file on GitHub · 140 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. yesterday First seen · 140 lines · 24 tokens per session scan A b26f5b5c4f17

Subscribe to this mod's changes

systematic-debugging is a skill published in the GitHub repository itallstartedwithaidea/agent-skills (36 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 1,353 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 2026-09-03.

Related

Other skills, from other repositories

update-saasmail

Sync the local saasmail repo with the latest upstream changes from https://github.com/choyiny/saasmail. Use this skill whenever the user wants to update saasmail, pull upstream changes, sync with upstream, rebase on upstream, get the latest saasmail, or says "/update-saasmail". Handles adding the upstream remote if…

choyiny/saasmail · 105 tokens

tracking-health

Preventive audit of conversion tracking across all configured ad platforms — Meta pixels + CAPI, Google Ads conversion actions, and final-URL tracking-parameter consistency on every platform — with a GA4 cross-check. Use when the user asks to check tracking, audit conversion measurement, verify pixels / tags, check…

logly/mureo · 168 tokens

story-html-publisher

Final step of the AI Storybook pipeline. Consolidates the scenes, images, and per-scene audio into ONE self-contained HTML storybook — a swipe/tap player with every image and audio clip embedded as base64 so the single file works offline and can be shared as-is. Reads {slug}scenes.json, {slug}images.json, and…

hassancs91/claude-image-generation · 207 tokens

learn

Save a marketing diagnosis insight to the pro-diagnosis knowledge base so it is applied in future operations across all platforms. Use when the user runs /learn, explicitly teaches the agent a marketing insight, corrects the agent's analysis, or asks to remember/record an operational learning for next time. Also use…

logly/mureo · 98 tokens

sealeap-amazon-product-targeting

Research, diagnose, and draft Amazon Ads ASIN and category product-targeting plans that complement keyword targeting, including audience expansion, competitor and category traffic, cross-sell, upsell, self-defense, negative targeting, placement analysis, and single-variable experiments. Use for 商品投放, ASIN 定向, 品类定向…

xjli360/sealeap-amazon-ad-skills · 168 tokens

weekly-report

Generate a weekly summary report across all platforms. Use when the user asks for a weekly report, summary, recap, end-of-week review, or weekly digest. Also use when the user asks in Japanese (週次レポート / 今週のまとめ / 週報を作成して).

logly/mureo · 63 tokens