root-cause-debugger

root-cause-debugger is a skill for Claude Code, Codex from beingmartinbmc/jambavan. It costs 55 tokens per session (721 once invoked), scanned A, original, MIT.

A step-by-step method for investigating bugs, failed tests, and unexpected behavior before suggesting a fix. It requires observing the evidence, comparing changes, forming a cause-based hypothesis, and then fixing it.

In plain words
What is it for?
Reproducing failures, reading complete error messages, checking recent changes, tracing bad data backward, adding focused diagnostics, and reassessing after repeated failed fixes.
Why use it?
It reduces guess-and-check debugging and encourages finding the mechanism that caused the failure.

Skill for Claude CodeCodex

Part of the jambavan plugin — 5 skills 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/beingmartinbmc/jambavan/root-cause-debugger
Any agent
npx skills add beingmartinbmc/jambavan --skill root-cause-debugger
Clone the repo
git clone --depth 1 https://github.com/beingmartinbmc/jambavan

Made for: Claude Code, Codex.

Or install jambavan, the plugin that ships this one along with the rest of its 5 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 root-cause-debugger

README.md
[![agentmods](https://agentmods.dev/badge/skills/beingmartinbmc/jambavan/root-cause-debugger.svg)](https://agentmods.dev/skills/beingmartinbmc/jambavan/root-cause-debugger)
Your own site
<a href="https://agentmods.dev/skills/beingmartinbmc/jambavan/root-cause-debugger"><img src="https://agentmods.dev/badge/skills/beingmartinbmc/jambavan/root-cause-debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 721 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 $0.00055 $0.00721
Opus 5 $0.00028 $0.00360
Sonnet 5 $0.00011 $0.00144
Haiku 4.5 $0.00006 $0.00072

Measured 4d ago against content hash 0d605aeba862, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

root-cause-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 4d 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/jambavan/skills/root-cause-debugger/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Root Cause Debugger

If the root_cause MCP tool is available, call it with the symptom (and attempts_so_far if this is not the first try) and use its output as an investigation checklist. Otherwise, follow the protocol below directly.

Evidence before fixes

Gather enough evidence to explain the likely failure mechanism before proposing a durable fix. If an urgent containment step is needed, label it as mitigation rather than root-cause resolution. After three unsuccessful fixes, pause and reassess assumptions, reproduction quality, and design boundaries; repeated failures do not by themselves prove the architecture is wrong.

Phase 1: Observe (before touching anything)

  1. Read the error completely. Stack traces, line numbers, error codes — do not skim.
  2. Reproduce consistently. Can you trigger it reliably? What are the exact steps?
  3. Check recent changes. What changed? git diff, recent commits, new deps, config.
  4. Trace data flow. Where does the bad value originate? Trace backward, not forward.

At multi-component boundaries, add the smallest safe diagnostic instrumentation needed:

  • Log what enters each component.
  • Log what exits each component.
  • Run to gather evidence showing where it breaks.
  • Remove temporary instrumentation when it is no longer needed, and do not log secrets.

Phase 2: Compare

  1. Find a working example of similar code in this codebase.
  2. List every difference between working and broken — however small.
  3. Do not assume "that can't matter."

Phase 3: Hypothesize and Test

  1. Form ONE hypothesis: "X is the root cause because Y."
  2. Make the SMALLEST possible change to test it.
  3. One variable at a time.
  4. Did it work? → Phase 4. Did not? → form a new hypothesis rather than stacking unverified fixes.

Phase 4: Fix

  1. Where practical, write or identify a failing test that reproduces the bug.
  2. Fix the root cause (not the symptom).
  3. Verify: test passes, no other tests broken.
  4. If 3+ fixes have failed, pause and discuss the evidence and next investigative step with the human.

Read the full file on GitHub · 65 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. 4d ago First seen · 65 lines · 55 tokens per session scan A 0d605aeba862

Subscribe to this mod's changes

root-cause-debugger is a skill published in the GitHub repository beingmartinbmc/jambavan (2 stars, last pushed 28d ago), licensed MIT. It adds 55 tokens to every session and 721 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

cix-workspace

Cross-project research workflow for cix workspaces in Claude Cowork. Use when a request spans multiple repositories — "wire feature X through the platform", "add Y across the services", "change Z in production/staging", "how does this work end-to-end across repos". Uses cixworkspacesearch to find which repos are in…

dvcdsys/code-index · 110 tokens

cix

Semantic code search and navigation across repositories indexed by a cix server, via the cix MCP tools. Use when finding code by meaning rather than exact strings — "find the authentication middleware", "where is X defined?", "what calls this function?", "how does Y work in this codebase?", "search the codebase for…

dvcdsys/code-index · 119 tokens

ai-unity-asset-pipeline

Build, install, run, and verify a reusable image-to-game-ready-3D pipeline for Unity with controlled ImageGen references, approved AI mesh providers, Blender MCP/CLI, modular era catalogs, Blender retopology/LOD/pivot processing, and Unity import/render proof. Use for 2D-to-3D assets, vehicles, aircraft, ships…

ezBuilder/code-brain · 95 tokens

source-command-cb-usage

코드브레인 활동 — Codex+Codex 토큰 + hook/MCP breakdown + PreToolUse 차단 횟수.

ezBuilder/code-brain · 36 tokens

source-command-cb-health

코드브레인 상태 한 줄 요약 — doctor·큐·worker·인덱스.

ezBuilder/code-brain · 28 tokens

billing-integrity

인앱결제·구독·쿼터 과금을 설계·구현·감사할 때 사용한다. 구독 무음 강등, 결제 검증 전수 실패, 이중/과다 차감, 웹훅 유실, 영구 무료 권한 같은 실제 사고를 막는 필수 항목과 감사 절차를 담았다. 스토어(Google Play·App Store) 연동, entitlement/게이트 판정, 영수증 검증, 웹훅·리컨사일, 멱등 원장 작업 전에 읽는다.

ezBuilder/code-brain · 130 tokens