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 commands/vishnu2kmohan/mcp-server-langgraph/quick-debuggit clone --depth 1 https://github.com/vishnu2kmohan/mcp-server-langgraphWhat 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 | $0.00006 | $0.03044 |
| Opus 5 | $0.00003 | $0.01522 |
| Sonnet 5 | $0.00001 | $0.00609 |
| Haiku 4.5 | $0.00001 | $0.00304 |
Grade A, and why
quick-debug scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:8080/healthz || echo "Service not responding" How it starts
The opening of the file, as written. The whole thing — 598 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quick Debug
Usage: /quick-debug or /quick-debug <error-message>
Purpose: Fast debugging workflow for common issues
🐛 What This Command Does
Provides AI-assisted debugging workflow to quickly identify and fix common issues:
- Analyzes error messages and stack traces
- Suggests likely causes based on patterns
- Recommends debugging steps
- Provides quick fixes for common problems
- Links to relevant code locations
🔍 Debugging Workflow
Step 1: Capture Error Information
If error message provided as argument:
# Use provided error
ERROR_MSG="$ARGUMENTS"
```bash
If no argument, look for recent errors:
```bash
# Check recent test failures
uv run --frozen pytest --lf -v 2>&1 | tee /tmp/test_errors.txt
# Check recent git commits for fix mentions
git log -10 --oneline | grep -i "fix"
# Check application logs (if running)
tail -50 logs/app.log 2>/dev/null || echo "No app logs found"
Step 2: Categorize Error Type
Analyze error message to determine category:
Import Errors:
ImportError: cannot import name 'X'
ModuleNotFoundError: No module named 'X'
→ Missing dependency, uncommitted code, wrong Python env
Test Failures:
AssertionError: X != Y
AttributeError: 'NoneType' object has no attribute 'X'
→ Logic error, missing mock, incorrect test setup
Runtime Errors:
RuntimeError: Event loop is closed
asyncio.TimeoutError: timeout exceeded
→ Async issues, resource management, timeouts
Type Errors:
TypeError: X() takes 2 positional arguments but 3 were given
mypy error: Argument has incompatible type
→ Function signature mismatch, type annotation issues
Database/Connection Errors:
ConnectionError: Failed to connect to Redis
sqlalchemy.exc.OperationalError
→ Service not running, configuration issue, network problem
Step 3: AI-Assisted Analysis
Provide context to Claude for analysis:
Analyzing error: {error_message}
Error Category: {category}
Recent Changes: {git log -5}
Modified Files: {git diff --name-only}
Test Status: {pytest status}
Please analyze this error and suggest:
1. Most likely root cause
2. Quick diagnostic steps
3. Potential fixes
4. Similar issues in codebase
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 · 598 lines · 6 tokens per session scan A 4417c47b9b7c
quick-debug is a command published in the GitHub repository vishnu2kmohan/mcp-server-langgraph (4 stars, last pushed 8d ago), licensed MIT. It adds 6 tokens to every session and 3,044 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
hal-voice-toggle
Toggle HAL 9000 voice clips on or off.
OPSX: Sync
Sync delta specs from a change to main specs.
domains
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
deps-age
Analyze dependency freshness and maintenance activity.
plan-delegate
Execution: work a roadmap as supervisor, brief an implementation agent per item, verify its work independently, then record and commit it.
setup
Command "setup" from jazz-max/ruflo-hub, covering setting up ruv-swarm hooks, quick start, 1. initialize with hooks, 2. test hook functionality and test pre-edit hook.