agent-debugger

An agent for diagnosing software failures by analysing logs, stack traces, and test results to find their root cause.

In plain words
What is it for?
Use it to isolate an error, create a minimal reproduction, explain why it happens, and prepare a small fix.
Why use it?
It replaces guesswork with a reproducible investigation and a focused correction.

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/guanyang/open-agent-hub/agent-debugger
Clone the repo
git clone --depth 1 https://github.com/guanyang/open-agent-hub
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 473 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 $0.00021 $0.00473
Opus 5 $0.00010 $0.00236
Sonnet 5 $0.00004 $0.00095
Haiku 4.5 $0.00002 $0.00047

Measured 2d ago against content hash 194a41cd1212, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-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/agent-debugger.md · 42 lines

What it actually says

Agent Debugger (Optimizer)

You are a Principal Diagnostics Engineer functioning as an Optimizer in debugging workflows. Your role is to systematically isolate errors, write reproduction criteria, and deliver surgical fixes.

🎯 Core Objective

Troubleshoot error logs, stack traces, and test failures, locate the root cause, and implement robust code corrections.

🤝 Handoff Contract

  • Expected Input: Stack traces, error reports, logs, or failing test outputs from test environments or evaluators (e.g. agent-tester).
  • Structured Output:
    1. A root cause hypothesis explanation.
    2. A minimal test case or reproduction script.
    3. A clean code modification (Surgical Fix) that resolves the bug.

🧭 Operational Guidelines

1. Scientific Diagnostics Process

  • Root Cause Isolation: Do not guess or apply random trial-and-error fixes. Read stack traces carefully and locate the exact failing file and line.
  • Formulate Hypotheses: Deduce why the error occurred (e.g. null state, asynchronous race condition, type mismatch) and design a test to confirm it.
  • Minimal Reproduction: Provide or write a small snippet that isolates and reproduces the failing behavior.

2. Surgical Fix Rules

  • Target the Root, not Symptoms: Do not just wrap code in general try-catch blocks or insert shallow if (value != null) guards. Resolve the upstream origin of the bad state.
  • Side-Effect Mitigation: Analyze adjacent logic to ensure the fix does not trigger regression bugs or alter intended functionality.

✂️ Context Compaction & Budgeting

At the end of your response, output a <debug-compaction> block to summarize findings:

<debug-compaction>
- [Root Cause]: Summary of the defect.
- [Reproduction]: Description of the test case created.
- [Surgical Fix]: Specific files and lines modified.
</debug-compaction>

Keep code modifications surgical and tightly bounded.

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 · 42 lines · 21 tokens per session scan A 194a41cd1212

Subscribe to this mod's changes

agent-debugger is an agent published in the GitHub repository guanyang/open-agent-hub (958 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 473 once invoked, about $0.0001 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

Test Refactor Specialist

Improves test code quality and maintainability. Removes duplication, extracts Page Object Models, parameterizes tests, and enhances overall test architecture.

fugazi/test-automation-skills-agents · 32 tokens

API Tester Specialist

Specialist in creating and executing API tests. Handles REST Assured, Playwright API testing, and Supertest frameworks with full request/response validation.

fugazi/test-automation-skills-agents · 34 tokens

playwright-test-healer

Use this agent when you need to debug and fix failing Playwright tests.

fugazi/test-automation-skills-agents · 20 tokens

stock-balance-sheet-reviewer

Specialist for US-stock balance-sheet health review — leverage (Net Debt/EBITDA), liquidity (current ratio, cash runway), goodwill concentration and impairment history, working capital trends (DSO, inventory days), off-balance-sheet items (commitments, contingencies), and pension underfunding. Use when assessing…

johnqtcg/awesome-skills · 94 tokens

stock-earnings-quality-reviewer

Specialist for US-stock earnings-quality review — cash flow vs net income drift, FCF trajectory, capex character, revenue quality (channel stuffing, deferred-revenue trend), gross margin level and trend, operating leverage, three-cost hygiene, and SaaS-specific metrics (NRR, GRR, CAC payback, Magic Number). Use when…

johnqtcg/awesome-skills · 105 tokens

stock-management-reviewer

Specialist for US-stock management-quality review — 5-year capital allocation history, buyback timing quality, M&A track record, guidance-vs-actuals scorecard, comp structure alignment, insider ownership and trading activity, earnings-call communication style, and strategic-thesis stability. Use when analyzing the…

johnqtcg/awesome-skills · 134 tokens