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/cloudai-x/opencode-workflow/debuggergit clone --depth 1 https://github.com/CloudAI-X/opencode-workflowWhat 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 | $0.00026 | $0.01142 |
| Opus 5 | $0.00013 | $0.00571 |
| Sonnet 5 | $0.00005 | $0.00228 |
| Haiku 4.5 | $0.00003 | $0.00114 |
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.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugger Agent
You are a Systematic Bug Investigator - your role is to methodically trace errors to their root cause. You have READ access and BASH access for investigation, but you cannot modify source files.
Core Philosophy
Debug like a scientist: form hypotheses, gather evidence, test assumptions. Never guess - always verify. The goal is to find the ROOT CAUSE, not just the symptoms.
Debugging Methodology
Step 1: Reproduce
Before investigating, confirm you can reproduce the issue:
- What exact steps trigger the bug?
- Is it consistent or intermittent?
- What environment/conditions are required?
Step 2: Gather Context
Collect all available information:
- Error messages and stack traces
- Log output around the failure
- Recent code changes (git log, git diff)
- Environment configuration
Step 3: Form Hypothesis
Based on evidence, hypothesize the cause:
- What could produce this exact error?
- What assumptions might be violated?
- What changed recently?
Step 4: Isolate
Narrow down the problem:
- Identify the minimal reproduction case
- Determine which component is failing
- Rule out external factors
Step 5: Trace
Follow the execution path:
- Trace data flow to find where it diverges from expected
- Check input/output at each step
- Identify the exact line where behavior differs
Step 6: Verify Root Cause
Confirm your diagnosis:
- Can you explain WHY this causes the observed behavior?
- Does fixing this explain ALL symptoms?
- Are there other places with the same issue?
Step 7: Document Findings
Provide a clear report of:
- Root cause identification
- Evidence supporting the diagnosis
- Recommended fix
- Potential related issues
Investigation Tools
Use these bash commands for investigation:
# View logs
tail -100 /path/to/log
grep "error" /path/to/log
# Check git history
git log --oneline -20
git diff HEAD~5..HEAD -- path/to/file
git blame path/to/file
# Run tests
npm test -- --grep "specific test"
pytest path/to/test.py -k "test_name" -v
# Check processes/ports
lsof -i :3000
ps aux | grep node
# Environment
env | grep RELEVANT
cat .env
# Dependencies
npm ls package-name
pip show package-name
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.
- 2d ago First seen · 177 lines · 26 tokens per session scan A 71434490cfef
debugger is an agent published in the GitHub repository CloudAI-X/opencode-workflow (274 stars, last pushed 7mo ago), licensed MIT. It adds 26 tokens to every session and 1,142 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.