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 commands/bherbruck/mcp-debugger/debuggit clone --depth 1 https://github.com/bherbruck/mcp-debuggerWhat 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 | $0.00015 | $0.00459 |
| Opus 5 | $0.00008 | $0.00230 |
| Sonnet 5 | $0.00003 | $0.00092 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
debug 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.
What it actually says
Debug Session
The MCP debugger tools are ALREADY AVAILABLE. Do NOT search for .mcp.json or config files. Just call the tools directly.
I'll help you debug $ARGUMENTS.file using the MCP debugger.
Instructions
-
Detect Language: First, determine the programming language from the file extension:
.py→ Python (uses debugpy).js,.ts,.mjs,.tsx→ JavaScript/TypeScript (uses vscode-js-debug).go→ Go (uses Delve).rs→ Rust (uses CodeLLDB)
-
Create Session: Use
create_debug_sessionwith the detected language -
Set Breakpoints: If a line number was provided, use
set_breakpointto add an initial breakpoint. Otherwise, suggest strategic breakpoints based on the code. -
Start Debugging: Use
start_debuggingwith the script path -
When Stopped: When the program pauses at a breakpoint:
- Use
get_source_contextto show the code around current location - Use
get_variablesto display local variables - Use
get_stack_traceto show the call stack - Explain what the code is doing at this point
- Use
-
Interactive Debugging:
- Ask if the user wants to step (in/over/out), continue, or inspect something
- Use
evaluate_expressionto test hypotheses about variable values - Use
expand_variableto drill into complex objects
-
Cleanup: When done, use
terminate_sessionto clean up
Tips
- Set breakpoints before where you expect the issue to occur
- Compare expected vs actual variable values
- Watch for null/undefined values or unexpected types
- Check loop counters and array indices
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 · 52 lines · 15 tokens per session scan A 8ddb38f42879
debug is a command published in the GitHub repository bherbruck/mcp-debugger (2 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 459 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.