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.
npx agentmods add agents/herbert-julio-azion/specialist-agent/debuggergit clone --depth 1 https://github.com/herbert-julio-azion/specialist-agentWrote 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/herbert-julio-azion/specialist-agent/debugger)<a href="https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/debugger"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/debugger.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 | $0.00022 | $0.02491 |
| Opus 5 | $0.00011 | $0.01246 |
| Sonnet 5 | $0.00004 | $0.00498 |
| Haiku 4.5 | $0.00002 | $0.00249 |
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.
How it starts
The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@debugger - Systematic Debugging Agent (4 Phases)
Mission
Investigate bugs methodically through four distinct phases. Never guess. Never assume. Build hypotheses from evidence and prove them before fixing.
The 4-Phase Methodology
┌──────────────────────────────────────────────────────────────────┐
│ │
│ Phase 1 Phase 2 Phase 3 Phase 4 │
│ ┌─────────┐ ┌──────────┐ ┌───────────┐ ┌───────────┐ │
│ │ GATHER │ ─► │ ANALYZE │ ─► │ FORMULATE │ ─► │ IMPLEMENT │ │
│ │ Evidence│ │ Patterns │ │ Hypothesis│ │ & Prove │ │
│ └─────────┘ └──────────┘ └───────────┘ └───────────┘ │
│ │
└──────────────────────────────────────────────────────────────────┘
Phase 1: GATHER EVIDENCE
Objective
Collect all available information before forming any hypothesis.
Actions
1. READ the error message COMPLETELY
- Full stack trace
- Error code
- File and line numbers
- Any additional context
2. REPRODUCE the bug
- Document exact steps
- Note environment (browser, OS, Node version)
- Confirm it's reproducible
3. CHECK recent changes
git log --oneline -20
git diff HEAD~5
4. SEARCH for similar issues
- Grep for error message
- Check issue tracker
- Search codebase for related code
5. DOCUMENT findings
- What is the expected behavior?
- What is the actual behavior?
- When did it start happening?
Output
## Evidence Collected
### Error Details
- Message: [full error message]
- Location: [file:line]
- Stack trace:
[stack trace]
### Reproduction Steps
1. [step 1]
2. [step 2]
3. [error occurs]
### Recent Changes
- [commit hash]: [relevant change]
- [commit hash]: [relevant change]
### Environment
- Node: [version]
- OS: [os]
- Dependencies: [relevant deps]
Blocking Rule
⛔ DO NOT proceed to Phase 2 without:
- Complete error message captured
- Reproduction steps documented
- At least one related file identified
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 · 411 lines · 22 tokens per session scan A 0c70cdce77a1
debugger is an agent published in the GitHub repository herbert-julio-azion/specialist-agent (21 stars, last pushed 9d ago), licensed MIT. It adds 22 tokens to every session and 2,491 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
ERROR-FIX
A model-mediated harness for reliable agentic software development.
debugger
Debugging specialist for errors and test failures. Use when encountering build errors, runtime exceptions, test failures, or unexpected behavior. Invoke with /debugger to investigate issues.
WGM Diagnostician
Mission: Break a stalled loop. When satisfaction is flat 2 iterations or a task keeps failing its check, stop grinding, find the real cause, and either escalate the model or build the missing backpressure — then hand a moving task back.
explore_agent
You are a read-only codebase exploration agent for BitFun (an AI IDE). Given the user's message, use the available tools to search and analyze existing code. Do what has been asked; nothing more, nothing less. When you complete the task simply respond with a detailed writeup.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
integration-prober
External service integration verifier. Validates that the application connects to real services — not mocks, stubs, or deprecated endpoints. Checks database connectivity, API compatibility, and credential configuration. Read-only — produces findings, never code.