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 skills add cosmicstack-labs/mercury-agent-skills --skill agent-task-delegationgit clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skillsWrote 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/skills/cosmicstack-labs/mercury-agent-skills/agent-task-delegation)<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/agent-task-delegation"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/agent-task-delegation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/agent-task-delegation"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/agent-task-delegation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 93 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00039 | $0.02964 |
| Opus 5 | $0.00019 | $0.01482 |
| Sonnet 5 | $0.00008 | $0.00593 |
| Haiku 4.5 | $0.00004 | $0.00296 |
Grade A, and why
agent-task-delegation 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 9d 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.
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 — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Task Delegation & Load Balancing
Overview
A multi-agent system without delegation logic is a mob, not a team. Tasks must be routed to the right agent, prioritized correctly, and balanced across available capacity. This skill covers queue-based architectures, routing strategies, backpressure handling, and dynamic scaling for production agent workloads.
Core Concepts
Delegation Models
| Model | Description | Best For |
|---|---|---|
| Direct Assignment | Task is routed to a specific agent by name | Known, fixed responsibilities |
| Work Queue | Tasks go into a queue; agents pull when ready | Variable workloads, many agents |
| Router | Classifier decides which agent handles each task | Heterogeneous task types |
| Supervisor | Orchestrator delegates and synthesizes | Complex multi-step workflows |
| Broadcast | All agents receive task; first responder claims it | Redundancy, SLA-critical tasks |
Load Balancing Strategies
| Strategy | Algorithm | When to Use |
|---|---|---|
| Round Robin | Cycle through agents in order | Identical agents, uniform tasks |
| Least Connections | Assign to agent with fewest active tasks | Variable task duration |
| Weighted | Based on agent capacity/priority | Heterogeneous agent capabilities |
| Consistent Hashing | Hash task → agent (deterministic) | Session affinity, cache locality |
| Latency-Based | Route to fastest available agent | Performance-sensitive tasks |
| Random | Pick agent at random | Simple, symmetrical setups |
Step-by-Step Implementation
Step 1: Build the Task Queue
from dataclasses import dataclass
from enum import Enum
import asyncio
import time
class Priority(Enum):
CRITICAL = 0
HIGH = 1
MEDIUM = 2
LOW = 3
@dataclass
class Task:
id: str
agent_type: str
payload: dict
priority: Priority = Priority.MEDIUM
created_at: float = None
timeout: int = 30
retry_count: int = 0
max_retries: int = 3
def __post_init__(self):
if self.created_at is None:
self.created_at = time.time()
class TaskQueue:
"""Priority-based task queue with timeout handling."""
def __init__(self):
self.queues = {
Priority.CRITICAL: asyncio.Queue(),
Priority.HIGH: asyncio.Queue(),
Priority.MEDIUM: asyncio.Queue(),
Priority.LOW: asyncio.Queue(),
}
async def enqueue(self, task: Task):
"""Add task to the appropriate priority queue."""
await self.queues[task.priority].put(task)
async def dequeue(self) -> Task:
"""Get the highest-priority available task."""
for priority in sorted([p for p in Priority]):
queue = self.queues[priority]
if not queue.empty():
task = await queue.get()
# Check if task has expired
if time.time() - task.created_at > task.timeout:
return await self.dequeue() # Skip expired task
return task
return None # All queues empty
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.
- 9d ago First seen · 381 lines · 39 tokens per session scan A 8bd9164b7fb7
agent-task-delegation is a skill published in the GitHub repository cosmicstack-labs/mercury-agent-skills (471 stars, last pushed 15d ago), licensed MIT. It adds 39 tokens to every session and 2,964 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 skills, from other repositories
modern-saas-builder
Founder-minded senior product engineer and SaaS architect skill. Use when building, planning, architecting, validating, designing, testing, securing, deploying, or monetizing modern SaaS products, micro-SaaS, web apps, AI agents, Web3/Base applications, agent commerce, or Telegram bots/Mini Apps. Always active when…
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.