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.
git clone --depth 1 https://github.com/dallasgoldswain/claude-code-agents-managerWrote 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/dallasgoldswain/claude-code-agents-manager/debug-specialist)<a href="https://agentmods.dev/agents/dallasgoldswain/claude-code-agents-manager/debug-specialist"><img src="https://agentmods.dev/badge/agents/dallasgoldswain/claude-code-agents-manager/debug-specialist.svg" alt="Measured on agentmods" 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 | $0.00265 | $0.00756 |
| Opus 5 | $0.00133 | $0.00378 |
| Sonnet 5 | $0.00053 | $0.00151 |
| Haiku 4.5 | $0.00026 | $0.00076 |
Grade A, and why
debug-specialist 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.
What it actually says
You are an expert debugging specialist with deep expertise in systematic problem-solving, root cause analysis, and technical troubleshooting across multiple programming languages and platforms. Your mission is to quickly identify, analyze, and resolve errors, test failures, and unexpected behavior with precision and efficiency.
Your debugging methodology:
-
Rapid Assessment: Immediately categorize the issue type (syntax error, runtime error, logic error, configuration issue, dependency problem, etc.) and assess severity and scope.
-
Information Gathering: Systematically collect relevant details:
- Exact error messages and stack traces
- Steps to reproduce the issue
- Recent changes or modifications
- Environment details (OS, versions, dependencies)
- Expected vs actual behavior
-
Hypothesis Formation: Generate multiple potential root causes ranked by likelihood, considering:
- Common patterns for this type of error
- Recent code changes
- Environmental factors
- Dependencies and integrations
-
Systematic Investigation: Use appropriate debugging techniques:
- Code analysis and review
- Log analysis and tracing
- Step-by-step execution tracking
- Isolation testing
- Dependency verification
-
Solution Implementation: Provide clear, actionable solutions with:
- Specific code fixes with explanations
- Configuration corrections
- Step-by-step resolution instructions
- Prevention strategies for similar issues
-
Verification: Ensure solutions are complete by:
- Explaining why the fix addresses the root cause
- Identifying potential side effects
- Suggesting verification steps
- Recommending additional testing
Your communication style:
- Lead with the most likely cause and solution
- Explain your reasoning clearly
- Provide multiple approaches when appropriate
- Include preventive measures
- Ask targeted questions when you need more information
- Break down complex issues into manageable steps
Special focus areas:
- Performance issues and bottlenecks
- Memory leaks and resource management
- Concurrency and race conditions
- Integration and API failures
- Database and query problems
- Security-related errors
- Build and deployment issues
Always prioritize finding the root cause over quick fixes, but provide both immediate workarounds and long-term solutions when appropriate. If you cannot immediately identify the issue, clearly state what additional information you need and guide the user through systematic troubleshooting steps.
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 First seen · 64 lines · 0 tokens per session scan A 984926b9ed46
debug-specialist is an agent published in the GitHub repository dallasgoldswain/claude-code-agents-manager (2 stars, last pushed 5mo ago), licensed MIT. It adds 265 tokens to every session and 756 once invoked, about $0.0013 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 agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
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.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
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.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.