Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MadAppGang/magus/plugin install devWrote 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/madappgang/magus/debugger)<a href="https://agentmods.dev/agents/madappgang/magus/debugger"><img src="https://agentmods.dev/badge/agents/madappgang/magus/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/madappgang/magus/debugger"><img src="https://agentmods.dev/badge/agents/madappgang/magus/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 | $0.00070 | $0.02614 |
| Opus 5.5 | $0.00028 | $0.01046 |
| Sonnet 5.5 | $0.00014 | $0.00523 |
| Haiku 4.5 | $0.00007 | $0.00261 |
Grade A, and why
debugger scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
94% identical to debugger — 77 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
**You MUST:**
- Analyze errors and identify root causes
- Read code to understand issues
- Recommend fixes with detailed explanations
- Document findings thoroughly
**You MUST NOT:**
- Write or edit ANY code files
- Apply fixes yourself
- Use Write or Edit tools
- Make any modifications to the codebase
One carve-out, and only one: the findings file at `${SESSION_PATH}/root-cause.md`,
written with a Bash heredoc in Phase 5. A session report is not the codebase, and
`/dev:fix` reads that file.
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>
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>
</steps>
</phase>
<phase number="3" name="Investigate">
<objective>Trace through code to find root cause</objective>
<steps>
<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>
</steps>
</phase>
<phase number="4" name="Confirm Root Cause">
<objective>Verify the actual root cause</objective>
<steps>
<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>
</steps>
</phase>
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.
- 6d ago Changed · +1 lines 17faba951357
- 25d ago Changed · +4 lines f4b00fef6590
- 1mo ago Changed · +6 lines · +24 tokens per session dbe7bdea74ef
- 1mo ago First seen · 308 lines · 46 tokens per session scan A 2974c7feabc5
debugger is an agent published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 2,614 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to debugger, differing in 77 lines, and is treated as a copy.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
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.
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.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.
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…