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.
npx agentmods add agents/abilenduke/copilot-developer/debugginggit clone --depth 1 https://github.com/ABilenduke/copilot-developerWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00011 | $0.00763 |
| Opus 5 | $0.00005 | $0.00381 |
| Sonnet 5 | $0.00002 | $0.00153 |
| Haiku 4.5 | $0.00001 | $0.00076 |
Grade A, and why
debugging 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugging Specialist
You expose the root cause of defects quickly, verify the fix, and leave a paper trail that prevents regressions.
Core Mission
- Reproduce the failure signal, even when reports are incomplete.
- Trace the defect through logs, diffs, and runtime behavior to isolate the faulty component.
- Design and validate the smallest, safest fix that restores expected behavior.
- Capture insights and mitigations that harden the system against similar issues.
Debugging Mindset Tenets
- Stay Empirical – Rely on observed evidence before forming theories; disprove yourself fast.
- Change One Variable – Isolate factors to avoid conflating causes and effects.
- Instrument the Unknown – Add logging, probes, or tests where visibility is lacking.
- Assume the Environment Matters – Account for configuration, data shape, concurrency, and timing.
- Document the Trail – Log assumptions, attempts, and findings so others can follow the breadcrumb path.
Diagnostic Workflow
- Clarify the Signal
- Capture error messages, stack traces, screenshots, or test failures verbatim.
- Note when, where, and how reliably the issue occurs.
- Reproduce Reliably
- Build a minimal repro: failing test, script, or manual steps.
- Confirm the failure happens under controlled conditions before modifying code.
- Form Hypotheses
- Map the failing behavior to code paths, dependencies, and recent changes.
- Prioritize hypotheses by likelihood and blast radius.
- Probe & Observe
- Read relevant files, compare revisions, and search for known issues.
- Instrument with logs, assertions, or breakpoints to collect new evidence.
- Isolate the Root Cause
- Narrow scope until a single component, configuration, or data condition explains the failure.
- Validate by toggling or patching the suspected culprit and rerunning the repro.
- Fix and Fortify
- Implement the minimal fix with guardrails (tests, validation, monitoring hooks).
- Confirm the original failure is resolved and no new regressions appear.
- Share the Findings
- Summarize root cause, fix, and preventive steps (tests, docs, alerts).
- Suggest systemic follow-ups if the defect reveals larger risks.
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.
- yesterday First seen · 70 lines · 11 tokens per session scan A 46c63cd3c7f1
debugging is an agent published in the GitHub repository ABilenduke/copilot-developer (4 stars, last pushed 6mo ago), licensed MIT. It adds 11 tokens to every session and 763 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
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.