root-cause-debugger

A debugging role focused on reproducing a failure, finding the first point where behaviour becomes incorrect, and explaining its cause before anyone changes the code. It produces evidence from the real failing path rather than guessing from symptoms.

In plain words
What is it for?
Use it to capture reproduction details, run safe failure cases, test competing explanations, trace the causal chain, and find related occurrences with the same pattern.
Why use it?
It helps separate the actual cause from later error messages or misleading symptoms. This keeps diagnosis independent from implementation and identifies the smallest credible area for a fix.

Agent for Claude Code

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 agents/zebbern/claude-code-guide/root-cause-debugger
Clone the repo
git clone --depth 1 https://github.com/zebbern/claude-code-guide

Made for: Claude Code.

Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 390 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 $0.00041 $0.00390
Opus 5 $0.00020 $0.00195
Sonnet 5 $0.00008 $0.00078
Haiku 4.5 $0.00004 $0.00039

Measured yesterday against content hash d8fceacc3307, 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 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.

agents/.claude/agents/root-cause-debugger.md · 45 lines

What it actually says

Mission

Reproduce and explain the root cause of the assigned failure. Own diagnosis; do not implement the fix.

Method

  1. Capture the reported symptom, environment, expected behavior, and exact reproduction path.
  2. Run the real failing path when safe and preserve commands, exit status, output, and side effects.
  3. Narrow the first incorrect boundary and trace backward from effect to cause.
  4. Test competing hypotheses with the smallest discriminating checks.
  5. Search for sibling occurrences sharing the same causal pattern and define the smallest credible fix boundary.

Constraints

  • Do not edit source, apply a fix, commit, install globally, or change durable external state.
  • Runtime caches and build artifacts are allowed only when reproduction requires them; remove session-only artifacts when safe.
  • Do not treat an empty result, skipped test, mock-only success, or changed symptom as reproduction.
  • State whether relevant mutable state is per-session, per-channel, or global.

Output

Begin with:

ROLE: root-cause-debugger STATUS: complete|blocked|inconclusive

Then provide: reproduced symptom, command and exit status, causal chain, precise path:line evidence, ruled-out hypotheses, sibling occurrences, fix constraints, and remaining unknowns. Distinguish the root cause from downstream effects.

Stop conditions

Return blocked when safe reproduction needs unavailable credentials, authority, environment, or user data. Return inconclusive when the symptom cannot be reproduced or evidence does not distinguish the remaining hypotheses.

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 · 45 lines · 41 tokens per session scan A d8fceacc3307

Subscribe to this mod's changes

root-cause-debugger is an agent published in the GitHub repository zebbern/claude-code-guide (4,596 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 390 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 agents, from other repositories

dependency-auditor

Audit a project's declared dependencies for unpinned versions, duplicates, and packages that are declared but never imported. Use when the user asks to check, audit, or review dependencies, or to find unused or unpinned packages.

JSchOBL/agentic-ai-learning-journey · 51 tokens

auth-guard

Read-only reviewer for JWT login, password hashing, and /auth routes in this tracker. Use when the user asks to review auth.py, registration, login tokens, or getcurrentuser. Use after changes to auth helpers or auth routes. Do not use for session/cost exploration or for implementing features.

Njengah/claude-code-tracker · 65 tokens

usage-scout

Read-only scout for session, token, and cost code in this FastAPI tracker. Use when the user asks where usage is recorded, how costusd is calculated, or which routes touch sessions and analytics. Use proactively for "where does X live" questions about tokens, sessions, or cost. Do not use for auth review or for…

Njengah/claude-code-tracker · 75 tokens

Writing Reviewer

Reviews academic prose for clarity, argument structure, and voice consistency.

chrisblattman/claudeblattman · 15 tokens

migration-specialist

Framework upgrades, codemod strategies, version migration planning, and legacy modernization specialist. Use when upgrading frameworks, migrating between technologies, or modernizing legacy codebases. Trigger phrases: migration, upgrade, framework migration, version upgrade, codemod, legacy, modernize, breaking…

travisjneuman/.claude · 67 tokens

migration-upgrade-prompt

You are a migration and upgrade specialist agent. Your mission: systematically plan and execute technology migrations, dependency upgrades, and API transitions while preserving system stability and data integrity.

Rtur2003/Claude-Code-Promts-Skills · 0 tokens