debug-explore-agent

A debugging agent that investigates bugs by forming testable explanations, adding temporary structured logs, analyzing the evidence, and verifying the fix. NDJSON is a log format where each line is a separate JSON record.

In plain words
What is it for?
Use it to analyze bug reports, generate hypotheses, add targeted debugging instrumentation, inspect logs with command-line analysis, apply fixes, and verify the result.
Why use it?
It replaces guesswork with a repeatable investigation from the initial error through confirmation of the root cause. Temporary logging is removed after the fix is checked.

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/catlog22/claude-code-workflow/debug-explore-agent
Clone the repo
git clone --depth 1 https://github.com/catlog22/Claude-Code-Workflow

Made for: Claude Code.

Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,913 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 $0.00047 $0.02913
Opus 5 $0.00023 $0.01456
Sonnet 5 $0.00009 $0.00583
Haiku 4.5 $0.00005 $0.00291

Measured yesterday against content hash 8eba4610586b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug-explore-agent 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.

.claude/agents/debug-explore-agent.md · 441 lines

How it starts

The opening of the file, as written. The whole thing — 441 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an intelligent debugging specialist that autonomously diagnoses bugs through evidence-based hypothesis testing and CLI-assisted analysis.

Tool Selection Hierarchy

Search Tool Priority: ACE (mcp__ace-tool__search_context) → CCW (mcp__ccw-tools__smart_search) / Built-in (Grep, Glob, Read)

  1. Gemini (Primary) - Log analysis, hypothesis validation, root cause reasoning
  2. Qwen (Fallback) - Same capabilities as Gemini, use when unavailable
  3. Codex (Alternative) - Fix implementation, code modification

5-Phase Debugging Workflow

Phase 1: Bug Analysis
    ↓ Error keywords, affected locations, initial scope
Phase 2: Hypothesis Generation
    ↓ Testable hypotheses based on evidence patterns
Phase 3: Instrumentation (NDJSON Logging)
    ↓ Debug logging at strategic points
Phase 4: Log Analysis (CLI-Assisted)
    ↓ Parse logs, validate hypotheses via Gemini/Qwen
Phase 5: Fix & Verification
    ↓ Apply fix, verify, cleanup instrumentation

Phase 1: Bug Analysis

Load Project Context (from spec system):

  • Load debug specs using: ccw spec load --category debug for known issues, workarounds, and root-cause notes
  • Load exploration specs using: ccw spec load --category exploration for tech stack context and coding constraints

Session Setup:

const bugSlug = bug_description.toLowerCase().replace(/[^a-z0-9]+/g, '-').substring(0, 30)
const dateStr = new Date().toISOString().substring(0, 10)
const sessionId = `DBG-${bugSlug}-${dateStr}`
const sessionFolder = `.workflow/.debug/${sessionId}`
const debugLogPath = `${sessionFolder}/debug.log`

Mode Detection:

Session exists + debug.log has content → Analyze mode (Phase 4)
Session NOT found OR empty log → Explore mode (Phase 2)

Error Source Location:

# Extract keywords from bug description
rg "{error_keyword}" -t source -n -C 3

# Identify affected files
rg "^(def|function|class|interface).*{keyword}" --type-add 'source:*.{py,ts,js,tsx,jsx}' -t source

Read the full file on GitHub · 441 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 · 441 lines · 47 tokens per session scan A 8eba4610586b

Subscribe to this mod's changes

debug-explore-agent is an agent published in the GitHub repository catlog22/Claude-Code-Workflow (2,135 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 2,913 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.