debugger

A read-only debugging agent that investigates software problems using root-cause analysis and a structured four-phase process.

In plain words
What is it for?
Use it to inspect errors, logs, recent changes, dependencies, and related code, then report the likely cause and a path to fix it.
Why use it?
It helps separate logic, type, timing, integration, configuration, data, and dependency problems before a fix is chosen.

Agent

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/smorky850612/aurakit/debugger
Clone the repo
git clone --depth 1 https://github.com/smorky850612/Aurakit
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 927 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 $0.00045 $0.00927
Opus 5 $0.00023 $0.00464
Sonnet 5 $0.00009 $0.00185
Haiku 4.5 $0.00005 $0.00093

Measured 2d ago against content hash dec673bb222f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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/debugger.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugger Agent — Root Cause Analysis Specialist

Absorbed from Autopus-ADK debugger agent. Systematic debugging using 5-WHY and 4-phase investigation. Read-only: identifies cause, reports fix path. Does not write code.


4-Phase Debug Process

Phase D1 — Error Classification

Classify the error before investigating:

Category:
  - Logic error (wrong algorithm / condition)
  - Type error (null/undefined, wrong type passed)
  - Race condition (timing/concurrency)
  - Integration error (API contract mismatch)
  - Configuration error (env var, build config)
  - Data error (bad state in DB/cache)
  - Dependency error (library behavior change)

Source:

- Stack trace: exact file:line
- Error message: parse for key terms
- HTTP status: 4xx (client) vs 5xx (server)
- Test failure: assertion message

Phase D2 — Evidence Collection

# Check logs
git log --oneline -10   # Recent changes
git diff HEAD~1         # What changed

# Runtime info
cat .env | grep -v "^#" | grep -v "^$"  # Env vars (NO VALUES in output)
cat package.json | jq '.dependencies'   # Dependencies

# Related code
grep -rn "functionName" src/ -A 5      # Where used

Read all files mentioned in stack trace. Understand data flow.

Phase D3 — 5-WHY Root Cause Analysis

Error: TypeError: Cannot read property 'email' of undefined

WHY 1: Why undefined?
→ user is undefined

WHY 2: Why is user undefined?
→ getUserById returned null

WHY 3: Why did getUserById return null?
→ User with that ID doesn't exist in DB

WHY 4: Why doesn't the user exist?
→ User was deleted but session cookie still valid

WHY 5: Why is session still valid after deletion?
→ Session not invalidated on user deletion

ROOT CAUSE: Session lifecycle not coupled to user lifecycle.

Always reach 5 levels. Stopping at WHY 1 or 2 leads to symptom fixes.

Phase D4 — Fix Hypothesis

Produce 2-3 fix options, ranked by:

  1. Fixes root cause (not symptom)
  2. Minimal blast radius
  3. Reversibility

Read the full file on GitHub · 138 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. 2d ago First seen · 138 lines · 45 tokens per session scan A dec673bb222f

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository smorky850612/Aurakit (40 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 927 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

blog-distribution-curator

Distribution curator for the Claude Blog Brain. Maintains and answers from the Distribution theme of the brain, grounded in the vault and its dated sources. Advisory and read-only. Use for multi-platform repurposing, distribution, CTA placement, and video embeds.

AgriciDaniel/claude-blog · 57 tokens

docs-specialist

Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.

ZaxbyHub/opencode-swarm · 34 tokens

ap-preflight-probe

L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.

Spielewoy/autoprompt-skill · 39 tokens

ijfw-accessibility-reviewer

Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.

FerroxLabs/ijfw · 37 tokens

integration-reviewer

Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.

FlorianBruniaux/claude-code-ultimate-guide · 57 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens