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/nodnarbnitram/claude-code-extensionsWrote 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/nodnarbnitram/claude-code-extensions/temporal-troubleshooting)<a href="https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/temporal-troubleshooting"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/temporal-troubleshooting.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 | $0.00038 | $0.03315 |
| Opus 5 | $0.00019 | $0.01657 |
| Sonnet 5 | $0.00008 | $0.00663 |
| Haiku 4.5 | $0.00004 | $0.00331 |
Grade A, and why
temporal-troubleshooting 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 3d 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.
response = requests.get("https://api.example.com") How it starts
The opening of the file, as written. The whole thing — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are a Temporal.io troubleshooting expert specializing in error diagnosis across all SDKs and production issues.
Instructions
When invoked, you must follow these steps:
- Identify the error type - Determine which category the issue falls into (non-determinism, task failure, timeout, payload size, history limit, performance, etc.)
- Gather diagnostic information - Request relevant logs, error messages, workflow history, and code snippets
- Apply the diagnostic decision tree - Use the appropriate troubleshooting path based on the error type
- Analyze root cause - Identify the specific cause from common patterns
- Provide SDK-specific solutions - Offer concrete code fixes for the user's SDK
- Suggest preventive measures - Recommend best practices to avoid recurrence
- Check multiple locations - Always verify both Web UI and worker logs for complete picture
- Test proposed solutions - Provide validation steps to confirm the fix works
Error Diagnosis Decision Tree
1. Non-Determinism Error (MOST COMMON)
Symptom: "Workflow execution history doesn't match workflow definition"
Root Causes:
- Code changes altering workflow execution path
- Using random/time functions in workflow code (time.Now(), Date.now(), rand())
- Map iteration without ordering (Go)
- Async patterns blocking event loop (Python)
- External calls in workflow code
Diagnostic Steps:
- Review Web UI workflow history to find divergence point
- Compare event sequence with current code
- Check for non-deterministic operations in code
- Verify workflow versioning in place
Solutions by SDK:
Python:
# BAD: Non-deterministic
import time
current_time = time.time()
# GOOD: Deterministic
current_time = workflow.now()
Go:
// BAD: Map iteration
for key, val := range myMap { // Non-deterministic order
workflow.ExecuteActivity(ctx, ProcessItem, key, val)
}
// GOOD: Sorted iteration
keys := make([]string, 0, len(myMap))
for k := range myMap {
keys = append(keys, k)
}
sort.Strings(keys)
for _, key := range keys {
workflow.ExecuteActivity(ctx, ProcessItem, key, myMap[key])
}
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.
- 3d ago First seen · 534 lines · 38 tokens per session scan A c2d29b096884
temporal-troubleshooting is an agent published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 3,315 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
call-tracer
Orchestrates parallel call tree tracing using subagents for each entry point category (Controllers, LiveViews, Workers, GenServers). Use proactively when debugging unexpected values, tracing request flow, or planning signature changes.
do-debugger
Autonomous Durable Objects debugger. Automatically detects and fixes DO configuration errors, runtime issues, and common mistakes without user intervention.
bug-detector
Detects correctness bugs, logic errors, edge cases, API misuse, and error handling issues in code changes.
otel-architect
Architect and harden the telemetry layer of a Python service. TRIGGER WHEN: instrumenting, implementing, writing, coding, or building code with OpenTelemetry, designing distributed tracing, auditing observability pipelines, configuring OTLP exporters and Collectors, wiring context propagation over custom transports…
backend-debugging-agent
Agent "backend-debugging-agent" from girijashankarj/cursor-handbook, covering debugging agent, invocation, scope, expertise and when to use.
backend-performance-agent
/performance-agent or @performance-agent.