step

A debugging command for moving through a program one step at a time. You can enter a called function, run the current line without entering it, or finish the current function and return to its caller.

In plain words
What is it for?
Use it during a debug session to step in, step over, or step out, then inspect the current source location and variable values before continuing or pausing execution.
Why use it?
It helps you inspect what code does and see how variable values change without running the whole program at once.

Command

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 commands/bherbruck/mcp-debugger/step
Clone the repo
git clone --depth 1 https://github.com/bherbruck/mcp-debugger
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 261 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 $0.00009 $0.00261
Opus 5 $0.00005 $0.00130
Sonnet 5 $0.00002 $0.00052
Haiku 4.5 $0.00001 $0.00026

Measured 2d ago against content hash f3b05f8ed747, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

step 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.

commands/step.md · 46 lines

What it actually says

Step Through Code

Stepping $ARGUMENTS.direction in the current debug session.

Step Directions

step in

Use step_in to:

  • Enter the next function call
  • Go into library code if needed
  • Useful when you want to understand what a function does

step over

Use step_over to:

  • Execute the current line completely
  • Move to the next line without entering function calls
  • Most common stepping action

step out

Use step_out to:

  • Complete the current function
  • Return to the caller
  • Useful when you've seen enough of the current function

After Each Step

  1. Use get_source_context to show where we are now
  2. Use get_variables to see current variable values
  3. Highlight any changes from the previous state
  4. Explain what just happened

Continue Execution

If you want to run until the next breakpoint instead of stepping:

  • Use continue to resume normal execution
  • Use pause to interrupt running code
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 · 46 lines · 9 tokens per session scan A f3b05f8ed747

Subscribe to this mod's changes

step is a command published in the GitHub repository bherbruck/mcp-debugger (2 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 261 once invoked, about $0.0000 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.