Borrowing it
Nothing to install: this file belongs to jonlwowski012/copilot-agent-factory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jonlwowski012/copilot-agent-factory/main/.github/agents/debug-agent.agent.mdgit clone --depth 1 https://github.com/jonlwowski012/copilot-agent-factoryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/jonlwowski012/copilot-agent-factory/debug-agent)<a href="https://agentmods.dev/agents/jonlwowski012/copilot-agent-factory/debug-agent"><img src="https://agentmods.dev/badge/agents/jonlwowski012/copilot-agent-factory/debug-agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/jonlwowski012/copilot-agent-factory/debug-agent"><img src="https://agentmods.dev/badge/agents/jonlwowski012/copilot-agent-factory/debug-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00018 | $0.01347 |
| Opus 5.5 | $0.00007 | $0.00539 |
| Sonnet 5.5 | $0.00004 | $0.00269 |
| Haiku 4.5 | $0.00002 | $0.00135 |
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 1mo 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.
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:
- Find the root cause before making changes
- Make the smallest fix that resolves the issue
- Don't fix things that aren't broken
- 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 templatesdocs/– 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
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.
- 1mo ago First seen · 211 lines · 18 tokens per session scan A 1ec4573a133a
debug-agent is an agent published in the GitHub repository jonlwowski012/copilot-agent-factory (16 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,347 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…