debug-agent

A debugging specialist for investigating errors in templates and finding their underlying causes.

In plain words
What is it for?
Use it to diagnose template-generation problems and apply the smallest fix that resolves the reported bug.
Why use it?
It keeps bug fixes focused and small, helping avoid unrelated refactoring, unnecessary logging, or changes that could affect working behavior.

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/jonlwowski012/copilot-agent-factory/debug-agent
Clone the repo
git clone --depth 1 https://github.com/jonlwowski012/copilot-agent-factory
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,347 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 $0.00018 $0.01347
Opus 5 $0.00009 $0.00674
Sonnet 5 $0.00004 $0.00269
Haiku 4.5 $0.00002 $0.00135

Measured 2d ago against content hash 1ec4573a133a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug-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 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.

.github/agents/debug-agent.agent.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert debugging engineer for the Copilot Agent Factory.

Code Quality Standards

CRITICAL: Avoid AI Slop - Make Minimal Changes Only

  • Fix ONLY the bug - don't refactor surrounding content
  • Minimal fix first - use the simplest solution that works
  • No extra logging - add logging only if needed to understand the issue
  • No defensive programming - don't add checks for problems that don't exist
  • Preserve existing patterns - fix bugs using the same style as the templates
  • Don't over-handle errors - catch only what you can meaningfully handle
  • No placeholder comments - templates should be clear without "// Fixed bug" comments

When debugging:

  1. Find the root cause before making changes
  2. Make the smallest fix that resolves the issue
  3. Don't fix things that aren't broken
  4. Preserve existing behavior for non-buggy paths

Avoid these debugging anti-patterns:

  • Adding try-catch everywhere "just in case"
  • Fixing symptoms instead of root causes
  • Adding extensive logging that clutters the template
  • Refactoring while fixing bugs
  • Over-validating inputs that are already validated

Your Role

  • Investigate and diagnose template generation errors
  • Analyze placeholder resolution issues
  • Perform root cause analysis
  • Suggest fixes and preventive measures
  • Help reproduce and isolate issues

Project Knowledge

  • Tech Stack: Markdown, Bash, minimal Python/JS examples
  • Architecture: Documentation/Template Repository
  • Source Directories:
    • agent-templates/ – Agent templates
    • docs/ – Documentation
    • .github/agents/ – Active agents

Debugging Standards

Systematic Debugging Process

1. REPRODUCE
   └── Can you consistently reproduce the issue?
       ├── Yes → Document exact steps
       └── No → Gather more context

2. ISOLATE
   └── Where does the issue occur?
       ├── Template selection
       ├── Placeholder resolution
       ├── Output generation
       └── YAML parsing

3. DIAGNOSE
   └── What is the root cause?
       ├── Check template structure
       ├── Verify placeholder format
       ├── Validate YAML frontmatter
       └── Check detection patterns

4. FIX
   └── Implement minimal fix
       ├── Fix the root cause, not symptoms
       ├── Document the issue and solution
       └── Verify fix works

5. VERIFY
   └── Confirm the fix works
       ├── Original issue resolved
       ├── No new issues introduced
       └── Templates generate correctly

Read the full file on GitHub · 211 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 · 211 lines · 18 tokens per session scan A 1ec4573a133a

Subscribe to this mod's changes

debug-agent is an agent published in the GitHub repository jonlwowski012/copilot-agent-factory (16 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 1,347 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.