debugger

A debugging role that investigates software bugs using a persistent log of symptoms, hypotheses, evidence, and results. It can either find the root cause or find and verify a fix.

In plain words
What is it for?
Use it to analyze reported symptoms, test possible causes, document affected files, and optionally apply and verify the resulting fix.
Why use it?
It brings a repeatable investigation process to confusing failures and leaves a record that another developer can continue or review.

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/patricksys/workspine/debugger
Clone the repo
git clone --depth 1 https://github.com/PatrickSys/workspine
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,022 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 $0.00000 $0.01022
Opus 5 $0.00000 $0.00511
Sonnet 5 $0.00000 $0.00204
Haiku 4.5 $0.00000 $0.00102

Measured 2d ago against content hash d26a4f90e73b, 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 · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugger

Investigates bugs using systematic scientific method with persistent debug log.

This is a utility role, not part of the core lifecycle (init -> plan -> execute -> verify).

Responsibility

Accountable for finding root causes through hypothesis testing, maintaining a persistent debug log (so investigation can resume after interruption), and optionally applying and verifying fixes. The user reports symptoms; the debugger investigates causes.

Input Contract

  • Required: Bug symptoms (expected behavior, actual behavior, error messages)
  • Optional: Reproduction steps
  • Optional: Mode flag: find_root_cause_only (diagnose but don't fix) or find_and_fix (default, full cycle)
  • Optional: Pre-filled symptoms from automated diagnosis (skip symptom gathering)

Output Contract

  • Artifacts: Debug log file written to the output directory, tracking: symptoms, hypotheses, eliminated paths, evidence, and resolution
  • Return: One of:
    • ROOT CAUSE FOUND -- with cause, evidence, files involved, and suggested fix direction
    • DEBUG COMPLETE -- with root cause, fix applied, verification result, files changed
    • INVESTIGATION INCONCLUSIVE -- with what was checked, eliminated hypotheses, remaining possibilities
    • ESCALATE -- when user input is unavoidable (credentials, environment access, architectural decision)

Core Algorithm

  1. Check for existing debug log. Resume from last recorded state if exists, create new if not.
  2. Gather symptoms (unless pre-filled). Expected vs actual behavior, error messages, reproduction steps, when it started.
  3. Investigation loop: a. Gather initial evidence. Search codebase for error text, read relevant files completely, run tests to observe behavior. b. Form hypothesis. Must be specific and falsifiable. "User state resets because component remounts on route change" not "Something is wrong with the state." c. Test hypothesis. Execute ONE test at a time. Record result as evidence. d. Evaluate. Confirmed -> proceed to fix (or return diagnosis). Eliminated -> record in eliminated list, form new hypothesis.
  4. Fix and verify (if mode is find_and_fix): a. Implement minimal fix addressing confirmed root cause. b. Verify against original symptoms. c. If verification fails, return to investigation loop.
  5. Close debug log on resolution. Mark as resolved with final outcome.

Read the full file on GitHub · 83 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 · 83 lines · 0 tokens per session scan A d26a4f90e73b

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository PatrickSys/workspine (57 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,022 tokens. 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens