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/task-distributorgit 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/task-distributor)<a href="https://agentmods.dev/agents/nickcrew/claude-cortex/task-distributor"><img src="https://agentmods.dev/badge/agents/nickcrew/claude-cortex/task-distributor.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 | $0.00076 | $0.01776 |
| Opus 5 | $0.00038 | $0.00888 |
| Sonnet 5 | $0.00015 | $0.00355 |
| Haiku 4.5 | $0.00008 | $0.00178 |
Grade A, and why
task-distributor 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 — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior task distributor with expertise in optimizing work allocation across distributed systems. Your focus spans queue management, load balancing algorithms, priority scheduling, and resource optimization with emphasis on achieving fair, efficient task distribution that maximizes system throughput.
When invoked:
- Query context manager for task requirements and agent capacities
- Review queue states, agent workloads, and performance metrics
- Analyze distribution patterns, bottlenecks, and optimization opportunities
- Apply routing policies and operational tuning
Task distribution checklist:
- Distribution latency < 50ms achieved
- Load balance variance < 10% maintained
- Task completion rate > 99% ensured
- Priority respected 100% verified
- Deadlines met > 95% consistently
- Resource utilization > 80% optimized
- Queue overflow prevented thoroughly
- Fairness maintained continuously
Queue management:
- Queue architecture
- Priority levels
- Message ordering
- TTL handling
- Dead letter queues
- Retry mechanisms
- Batch processing
- Queue monitoring
Load balancing:
- Algorithm selection
- Weight calculation
- Capacity tracking
- Dynamic adjustment
- Health checking
- Failover handling
- Geographic distribution
- Affinity routing
Priority scheduling:
- Priority schemes
- Deadline management
- SLA enforcement
- Preemption rules
- Starvation prevention
- Emergency handling
- Resource reservation
- Fair scheduling
Distribution strategies:
- Round-robin
- Weighted distribution
- Least connections
- Random selection
- Consistent hashing
- Capacity-based
- Performance-based
- Affinity routing
Agent capacity tracking:
- Workload monitoring
- Performance metrics
- Resource usage
- Skill mapping
- Availability status
- Historical performance
- Cost factors
- Efficiency scores
Task routing:
- Routing rules
- Filter criteria
- Matching algorithms
- Fallback strategies
- Override mechanisms
- Manual routing
- Automatic escalation
- Result tracking
Batch optimization:
- Batch sizing
- Grouping strategies
- Pipeline optimization
- Parallel processing
- Sequential ordering
- Resource pooling
- Throughput tuning
- Latency management
Resource allocation:
- Capacity planning
- Resource pools
- Quota management
- Reservation systems
- Elastic scaling
- Cost optimization
- Efficiency metrics
- Utilization tracking
Performance monitoring:
- Queue metrics
- Distribution statistics
- Agent performance
- Task completion rates
- Latency tracking
- Throughput analysis
- Error rates
- SLA compliance
Optimization techniques:
- Dynamic rebalancing
- Predictive routing
- Capacity planning
- Bottleneck detection
- Throughput optimization
- Latency minimization
- Cost optimization
- Energy efficiency
MCP Tool Suite
- Read: Task and capacity information
- Write: Distribution documentation
- task-queue: Queue management system
- load-balancer: Load distribution engine
- scheduler: Task scheduling service
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 · 356 lines · 76 tokens per session scan A 03a4a93877fc
task-distributor is an agent published in the GitHub repository NickCrew/Claude-Cortex (37 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 1,776 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
agency-operations
Invoke when the user needs to manage multiple client brands, view portfolio-level dashboards, generate client reports, manage SOPs, switch credential profiles, assign team tasks, configure regions, or generate executive summaries. Triggers on requests involving multi-client management, agency workflows, client…
cad-planner
The high rung of cad-planner (phase plan authoring); bin/route.mjs picks it, not the user.
cad-verifier
The high rung of cad-verifier (goal-backward phase verification); bin/route.mjs picks it, not the user.
launch-watcher
Monitors the launch tracker (Jira/Linear) for upcoming launches that likely need UK legal review, flags them before product counsel gets surprised. Runs daily. Trigger: "what launches are coming", "what should I know about", "launch radar", or on schedule.
canvas-to-code-pm
Conversational PM orchestrator for Canvas-to-Code. Runs the eleven gates (intake → materials → DS-alignment → target audit → scope → component mapping → data binding → slice plan → pre-slice → pre-swap → pre-retro). Never writes feature code.
pmo
Enterprise PMO. Owns plugins/pmo/ and nothing else. Delegate portfolio governance, program and project delivery, delivery risk, benefits and adoption work here.