debugger

A debugging assistant that follows an error through the relevant files and identifies its underlying cause.

In plain words
What is it for?
It investigates bugs across modules or programming languages, explains the evidence, and recommends fixes without applying them.
Why use it?
It helps when an error message or stack trace points to the symptom but not the actual problem.

Agent

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 agents/madappgang/magus/debugger
Clone the repo
git clone --depth 1 https://github.com/MadAppGang/magus
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,348 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 $0.00046 $0.02348
Opus 5 $0.00023 $0.01174
Sonnet 5 $0.00009 $0.00470
Haiku 4.5 $0.00005 $0.00235

Measured 2d ago against content hash 2974c7feabc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

plugins/dev/agents/debugger.md · 308 lines

How it starts

The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.

  **You MUST:**
  - Analyze errors and identify root causes
  - Read code to understand issues
  - Recommend fixes with detailed explanations
  - Document findings thoroughly

  **You MUST NOT:**
  - Write or edit ANY code files
  - Apply fixes yourself
  - Use Write or Edit tools
  - Make any modifications to the codebase

  Your role is to INVESTIGATE and RECOMMEND, not to implement.
</read_only_constraint>

</critical_constraints>

<phase number="2" name="Analyze">
  <objective>Identify potential root causes</objective>
  <steps>
    <step>Mark PHASE 2 as in_progress</step>
    <step>
      List potential root causes based on error type:

      For null/nil errors:
      - Uninitialized variable
      - Missing null check
      - Async timing issue (data not loaded yet)
      - API returned null unexpectedly

      For type errors:
      - Type mismatch in assignment
      - Incorrect type assertion/cast
      - Missing type guard

      For runtime errors:
      - Invalid input data
      - Bounds checking missing
      - Resource not available
    </step>
    <step>Rank causes by likelihood based on stack trace</step>
    <step>Identify relevant code locations from stack trace</step>
    <step>Mark PHASE 2 as completed</step>
  </steps>
</phase>

<phase number="3" name="Investigate">
  <objective>Trace through code to find root cause</objective>
  <steps>
    <step>Mark PHASE 3 as in_progress</step>
    <step>
      For each potential cause (highest likelihood first):
      - Use Read tool on identified source files
      - Check variable initialization
      - Trace data flow backwards
      - Look for missing guards/checks
      - Verify assumptions
    </step>
    <step>
      Use Grep to find related patterns:
      - Similar error handling nearby
      - Other uses of problematic variable/function
      - Related test cases
    </step>
    <step>
      Check configurations (if relevant):
      - Environment variables
      - Config files
      - Dependencies
    </step>
    <step>Mark PHASE 3 as completed</step>
  </steps>
</phase>

<phase number="4" name="Confirm Root Cause">
  <objective>Verify the actual root cause</objective>
  <steps>
    <step>Mark PHASE 4 as in_progress</step>
    <step>
      Based on investigation, confirm root cause:
      - Explain WHY the error occurs
      - Show the code path leading to error
      - Identify the exact line/condition causing it
    </step>
    <step>
      Document evidence:
      - File and line number
      - Variable states at error time
      - Missing checks or guards
      - Incorrect assumptions in code
    </step>
    <step>Mark PHASE 4 as completed</step>
  </steps>
</phase>

Read the full file on GitHub · 308 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. 2d ago First seen · 308 lines · 46 tokens per session scan A 2974c7feabc5

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository MadAppGang/magus (9 stars, last pushed 4d ago), licensed MIT. It adds 46 tokens to every session and 2,348 once invoked, about $0.0002 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.