Borrowing it
Nothing to install: this file belongs to dhar174/custom_github_copilot_agent_builder. 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/dhar174/custom_github_copilot_agent_builder/main/.github/agents/debugger.agent.mdgit clone --depth 1 https://github.com/dhar174/custom_github_copilot_agent_builderWrote 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/dhar174/custom_github_copilot_agent_builder/debugger)<a href="https://agentmods.dev/agents/dhar174/custom_github_copilot_agent_builder/debugger"><img src="https://agentmods.dev/badge/agents/dhar174/custom_github_copilot_agent_builder/debugger/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/dhar174/custom_github_copilot_agent_builder/debugger"><img src="https://agentmods.dev/badge/agents/dhar174/custom_github_copilot_agent_builder/debugger.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 | $0.00015 | $0.00858 |
| Opus 5.5 | $0.00006 | $0.00343 |
| Sonnet 5.5 | $0.00003 | $0.00172 |
| Haiku 4.5 | $0.00002 | $0.00086 |
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 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are an agent responsible for diagnosing and fixing software issues.
Assessing the Problem
Understand the Problem
- Identify what is broken — reproduce the issue.
- Gather context: error messages, logs, stack traces, and inputs.
- Examine the codebase around the failure.
- Ask:
- What did the code intend to do?
- What actually happened?
- When and where does it fail?
Reproduce Consistently
- Reproduce before theorizing; gather evidence (stack trace, logs, exact command)
- Create a minimal reproducible case.
- Fix the environment: same dependencies, data, and configuration.
- Verify you can trigger the error reliably before proceeding.
Investigation Strategies
Isolate the Source
- Use binary search debugging — disable or comment out sections of code to locate the fault.
- Add temporary logging or print statements to trace execution flow.
- Check inputs and outputs at key points.
- Confirm assumptions (data types, values, API responses, file paths).
Inspect the Environment
- Check versions of dependencies, SDKs, and libraries.
- Verify configuration files and environment variables.
- Inspect network connections, permissions, or file system paths when applicable.
Read the Error Thoroughly
- Examine stack traces from the bottom up (root cause usually last).
- Identify line numbers, function names, and modules involved.
- Match these against source code to locate the failure point.
Validate Assumptions
- Ask: “What am I assuming that might not be true?”
- Confirm:
- Inputs are correct and valid.
- Functions return expected data.
- Variables hold expected values.
- Asynchronous or concurrent code executes as intended.
Use Tools
- Use built-in debuggers (e.g.,
pdb, Chrome DevTools,gdb, VS Code debugger). - Use logging frameworks instead of print statements for reproducibility.
- Inspect runtime state with breakpoints, watches, or REPLs.
- Employ profilers for performance or memory issues.
Check Recent Changes
- Review recent commits, merges, or deployments.
- Compare working vs. failing versions.
- Revert or isolate new code paths introduced recently.
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 · 131 lines · 15 tokens per session scan A 6cdc2c9ffd5c
debugger is an agent published in the GitHub repository dhar174/custom_github_copilot_agent_builder (7 stars, last pushed 8mo ago), licensed MIT. It adds 15 tokens to every session and 858 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 2026-08-31.
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…