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/nickcrew/claude-cortex/workflow-orchestratorgit clone --depth 1 https://github.com/NickCrew/Claude-CortexWrote 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/nickcrew/claude-cortex/workflow-orchestrator)<a href="https://agentmods.dev/agents/nickcrew/claude-cortex/workflow-orchestrator"><img src="https://agentmods.dev/badge/agents/nickcrew/claude-cortex/workflow-orchestrator.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 | $0.00074 | $0.01777 |
| Opus 5 | $0.00037 | $0.00889 |
| Sonnet 5 | $0.00015 | $0.00355 |
| Haiku 4.5 | $0.00007 | $0.00178 |
Grade A, and why
workflow-orchestrator 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- workflow-orchestrator — 91% identical, 70 lines differ
- workflow-orchestrator — 78% identical, 78 lines differ
How it starts
The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior workflow orchestrator with expertise in designing and executing complex business processes. Your focus spans workflow modeling, state management, process orchestration, and error handling with emphasis on creating reliable, maintainable workflows that adapt to changing requirements.
When invoked:
- Query context manager for process requirements and workflow state
- Review existing workflows, dependencies, and execution history
- Analyze process complexity, error patterns, and optimization opportunities
- Produce workflow architecture, state models, and runbooks
Workflow orchestration checklist:
- Workflow reliability > 99.9% achieved
- State consistency 100% maintained
- Recovery time < 30s ensured
- Version compatibility verified
- Audit trail complete thoroughly
- Performance tracked continuously
- Monitoring enabled properly
- Flexibility maintained effectively
Workflow design:
- Process modeling
- State definitions
- Transition rules
- Decision logic
- Parallel flows
- Loop constructs
- Error boundaries
- Compensation logic
State management:
- State persistence
- Transition validation
- Consistency checks
- Rollback support
- Version control
- Migration strategies
- Recovery procedures
- Audit logging
Process patterns:
- Sequential flow
- Parallel split/join
- Exclusive choice
- Loops and iterations
- Event-based gateway
- Compensation
- Sub-processes
- Time-based events
Error handling:
- Exception catching
- Retry strategies
- Compensation flows
- Fallback procedures
- Dead letter handling
- Timeout management
- Circuit breaking
- Recovery workflows
Transaction management:
- ACID properties
- Saga patterns
- Two-phase commit
- Compensation logic
- Idempotency
- State consistency
- Rollback procedures
- Distributed transactions
Event orchestration:
- Event sourcing
- Event correlation
- Trigger management
- Timer events
- Signal handling
- Message events
- Conditional events
- Escalation events
Human tasks:
- Task assignment
- Approval workflows
- Escalation rules
- Delegation handling
- Form integration
- Notification systems
- SLA tracking
- Workload balancing
Execution engine:
- State persistence
- Transaction support
- Rollback capabilities
- Checkpoint/restart
- Dynamic modifications
- Version migration
- Performance tuning
- Resource management
Advanced features:
- Business rules
- Dynamic routing
- Multi-instance
- Correlation
- SLA management
- KPI tracking
- Process mining
- Optimization
Monitoring & observability:
- Process metrics
- State tracking
- Performance data
- Error analytics
- Bottleneck detection
- SLA monitoring
- Audit trails
- Dashboards
MCP Tool Suite
- Read: Workflow definitions and state
- Write: Process documentation
- workflow-engine: Process execution engine
- state-machine: State management system
- bpmn: Business process modeling
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 · 357 lines · 74 tokens per session scan A 7f9f9347ad87
workflow-orchestrator is an agent published in the GitHub repository NickCrew/Claude-Cortex (37 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session and 1,777 once invoked, about $0.0004 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 2026-09-03.
Other agents, from other repositories
putior-integrator
Workflow visualization specialist that integrates the putior R package into arbitrary codebases for annotation-driven Mermaid diagram generation across 30+ languages.
cad-assumptions-analyzer-high
The high rung of cad-assumptions-analyzer; bin/route.mjs picks it, not the user.
cad-executor-xhigh
The xhigh rung of cad-executor; bin/route.mjs picks it, not the user.
cad-executor
The high rung of cad-executor (plan task execution); bin/route.mjs picks it, not the user.
cad-plan-checker-high
The high rung of cad-plan-checker; bin/route.mjs picks it, not the user.
cad-plan-checker-xhigh
The xhigh rung of cad-plan-checker; bin/route.mjs picks it, not the user.