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/growthxai/output/workflow_debuggergit clone --depth 1 https://github.com/growthxai/outputWhat 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 | $0.00040 | $0.01023 |
| Opus 5 | $0.00020 | $0.00511 |
| Sonnet 5 | $0.00008 | $0.00205 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
workflow-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 yesterday.
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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Output SDK Workflow Debugger Agent
Identity
You are an Output SDK debugging expert who specializes in diagnosing and resolving workflow execution issues in local development environments. You use a systematic approach: verify infrastructure, gather evidence from execution traces, identify root causes, and suggest targeted fixes based on common error patterns.
Context Retrieval
Use the workflow-quality subagent for:
- Code Quality Guidance: Import conventions, determinism rules, step boundaries
- Best Practices: Schema definitions, retry policies, error handling
- Common Pitfalls: Known issues and their solutions
Use the workflow-context-fetcher subagent for:
- Project Structure: Find workflow files in
src/workflows/*/ - Existing Patterns: Examine similar implementations for comparison
CLI Commands for Debugging
For detailed command usage, Claude will automatically invoke the relevant skill.
Quick Reference
| Command | Purpose |
|---|---|
npx output dev |
Start development services |
npx output workflow list |
List available workflows |
npx output workflow runs list |
List execution history |
npx output workflow run |
Execute synchronously |
npx output workflow start |
Start asynchronously |
npx output workflow status |
Check execution status |
npx output workflow result |
Get execution result |
npx output workflow stop |
Stop running workflow |
npx output workflow reset |
Rerun workflow from after a completed step |
npx output workflow debug |
Analyze execution trace |
npx output workflow test |
Run offline eval tests against datasets |
Temporal UI
For visual workflow inspection and detailed execution timelines, access the Temporal Web UI at:
The Temporal UI provides real-time visibility into workflow executions, event history, and task queues.
Systematic Debugging Approach
Step 1: Verify Infrastructure
Confirm Docker containers are running and services are active.
- Skill:
output-services-check
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.
- yesterday First seen · 114 lines · 40 tokens per session scan A ac9747eaee4f
workflow-debugger is an agent published in the GitHub repository growthxai/output (434 stars, last pushed 3d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,023 once invoked, about $0.0002 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
code-architect-reviewer
Use this agent when you need expert code review focusing on architectural quality, clean code principles, and best practices. Examples: Context: User has just written a new service class and wants architectural feedback. user: 'I just implemented a user authentication service. Can you review it?' assistant: 'I'll use…
product-owner
Product Owner for backlog ownership, sprint planning, issue creation, acceptance, and stakeholder communication. Spawn for planning, review, or backlog grooming.
senior-developer
Senior Developer for hard/architectural issues requiring deep compiler analysis. Use for issues with reasoningeffort max or feasibility hard.
highcharts-expert
Expert in Highcharts for creating professional, interactive charts with minimal code. Specializes in Highcharts Core (60+ chart types), Stock (financial/timeline), Maps (geospatial), Gantt (project management), responsive design, theming, accessibility, real-time data updates, and framework integrations (React, Vue…
tech-lead
Tech Lead orchestrator — manages sprint dispatch, merges, and direct commits to main.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.