systematic-debugging

systematic-debugging is a skill for Claude Code, Codex from jcwleo/oh-no-harness. It costs 36 tokens per session (3,928 once invoked), scanned A, original, MIT.

A step-by-step method for finding the root cause of software failures, regressions, flaky tests, or unexpected results. It requires reproducing the problem and recording possible explanations before changing code.

In plain words
What is it for?
Use it to investigate failing tests, intermittent failures, regressions, and other bugs whose cause is not yet known.
Why use it?
It reduces guesswork and prevents fixing only the line where an error appears when the bad value may have originated elsewhere.

Skill for Claude CodeCodex

Part of the oh-no-harness plugin — 12 skills, 12 commands, 9 agents, 1 hook 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/jcwleo/oh-no-harness/systematic-debugging
Any agent
npx skills add jcwleo/oh-no-harness --skill systematic-debugging
Clone the repo
git clone --depth 1 https://github.com/jcwleo/oh-no-harness

Made for: Claude Code, Codex.

Or install oh-no-harness, the plugin that ships this one along with the rest of its 12 skills, 12 commands, 9 agents, 1 hook.

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/jcwleo/oh-no-harness/systematic-debugging.svg)](https://agentmods.dev/skills/jcwleo/oh-no-harness/systematic-debugging)
Your own site
<a href="https://agentmods.dev/skills/jcwleo/oh-no-harness/systematic-debugging"><img src="https://agentmods.dev/badge/skills/jcwleo/oh-no-harness/systematic-debugging.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,928 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 5.1 $0.00036 $0.03928
Opus 5 $0.00018 $0.01964
Sonnet 5 $0.00007 $0.00786
Haiku 4.5 $0.00004 $0.00393

Measured 5d ago against content hash d6819c3d1d43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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.

plugins/oh-no-harness/skills-claude/systematic-debugging/SKILL.md · 318 lines

How it starts

The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Systematic Debugging for Claude Code

This generated file is the Claude Code-facing runtime skill document. Claude Code slash commands should read this file directly; maintainers edit the source documents listed below instead.

Generated Runtime Composition

Source order:

  • ../../docs/skill-core/systematic-debugging.md
  • ../../docs/platforms/claude-code-systematic-debugging.md

The sections below are already composed for this platform. Do not ask the runtime model to load another platform's runtime document or invocation syntax.

Source: docs/skill-core/systematic-debugging.md

Systematic Debugging

Find the root cause before changing behavior. This is the direct debugging entry point for failures that do not need the full ralph execution loop; do not use it for greenfield feature work — use ralplan or ralph when the task is broader than a bounded failure.

Invariants

D1. Reproduce (or explain why reproduction is blocked) before changing any
    code; never fix from a stack-trace line when the bad value originated
    elsewhere.
D2. A hypothesis ledger precedes diagnostic dispatch and deep investigation:
    one recorded hypothesis for an obvious localized failure; 2-3 competing
    hypotheses for unknown, nontrivial, flaky, repeated, or cross-boundary
    failures.
D3. A root cause is confirmed falsifiably by a causal toggle — toggling the
    suspected cause makes the failure appear and reverting makes it
    disappear; when a clean toggle is not feasible, state why and name the
    next-strongest confirming evidence.
D4. The minimal fix is applied only after root cause and reproduction
    evidence exist; behavior fixes create a failing reproduction test
    first (read and follow `test-driven-development`).
D5. Respect the active caller's stricter failed-fix budget and escalation
    route; without one, stop and route back to the user or `ralplan` after
    three failed fix attempts. Also route back on architecture-level coupling
    or a fix that would change broad APIs, product behavior, data handling,
    security, or delivery scope; do not directly dispatch
    `plan-reviewer` — planning review is Ralplan-owned.
D6. `fusion-rescue` is a bounded internal escalation when diagnostics
    stall; it returns control here before any fix is applied.
D7. The main agent orchestrates and owns `.oh-no` state. Diagnostic and
    evidence roles dispatch by default, and confirmed repository work-product
    fixes dispatch `executor`; inline mutation is only a recorded LIGHT-tiny
    or dispatch-unavailable fallback.
D8. The verification evidence must show the failure mode is gone, not only
    that the current trigger no longer appears in this environment.
D9. Mid-loop skill: after verification, return the result to the caller
    (`ralph`, `ultrawork`, or direct invocation); never chain to another
    workflow skill.

Read the full file on GitHub · 318 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. 5d ago First seen · 318 lines · 36 tokens per session scan A d6819c3d1d43

Subscribe to this mod's changes

systematic-debugging is a skill published in the GitHub repository jcwleo/oh-no-harness (11 stars, last pushed 28d ago), licensed MIT. It adds 36 tokens to every session and 3,928 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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens