debug

debug is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (574 once invoked), scanned A, original, MIT.

An interactive debugger for pausing and inspecting a source file, test, or running program while it executes.

In plain words
What is it for?
It starts debug sessions, sets breakpoints at chosen lines, runs tests under their detected test runner, and supports step-by-step inspection.
Why use it?
It helps developers examine what the program is doing at a specific point instead of guessing why it failed.

Command for Claude Code

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/samibs/skillfoundry/debug
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code.

Wrote 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.

agentmods badge for debug

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/debug.svg)](https://agentmods.dev/commands/samibs/skillfoundry/debug)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/debug"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/debug.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 574 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 $0.00000 $0.00574
Opus 5 $0.00000 $0.00287
Sonnet 5 $0.00000 $0.00115
Haiku 4.5 $0.00000 $0.00057

Measured yesterday against content hash a6cd80856467, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/commands/debug.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug — Interactive Debugger

Role: Launch and control an interactive debug session for a file, test, or running process.


Usage

/debug <file>              Start debug session, paused at entry
/debug <file>:<line>       Start session with breakpoint at line
/debug test <test-file>    Debug a test file using its test runner

Examples

/debug src/auth/login.ts
/debug src/utils/parser.ts:42
/debug test src/auth/__tests__/login.test.ts

Behavior

When invoked, follow this sequence:

1. Start Session

  • Parse the argument to extract file path and optional line number.
  • If prefixed with test, detect the test runner (jest, vitest, pytest, mocha) from project config.
  • Call debug_start with the resolved file, runtime, and test_command if applicable.
  • Confirm the session started and report the paused location.

2. Set Initial Breakpoint (if line specified)

  • If the user provided <file>:<line>, call debug_breakpoint with action set at that line.
  • Then call debug_step with action continue to run to the breakpoint.
  • Report the paused location and surrounding code context.

3. Guide Inspection

  • Once paused, call debug_inspect with target scope to show local variables.
  • Call debug_inspect with target callstack to show the call stack.
  • Present findings and ask the user what to investigate next.

4. Interactive Loop

Respond to user instructions by mapping them to debug tools:

User says Tool call
"step" / "next" debug_step action=next
"step into" debug_step action=into
"step out" debug_step action=out
"continue" debug_step action=continue
"inspect X" debug_inspect target=X
"eval " debug_evaluate expression=expr
"break :" debug_breakpoint action=set
"breakpoints" debug_breakpoint action=list
"stop" / "quit" debug_stop

5. Cleanup

  • Always call debug_stop when the user is done or the process exits.
  • Report any uncaught exceptions with full stack trace and variable context.

Read the full file on GitHub · 76 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. yesterday First seen · 76 lines · 0 tokens per session scan A a6cd80856467

Subscribe to this mod's changes

debug is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 574 tokens. 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 2026-09-03.