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 omnigentx/jarvis --skill delegation-strategygit clone --depth 1 https://github.com/omnigentx/jarvisWrote 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/omnigentx/jarvis/delegation-strategy)<a href="https://agentmods.dev/skills/omnigentx/jarvis/delegation-strategy"><img src="https://agentmods.dev/badge/skills/omnigentx/jarvis/delegation-strategy/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/omnigentx/jarvis/delegation-strategy"><img src="https://agentmods.dev/badge/skills/omnigentx/jarvis/delegation-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.00648 |
| Opus 5 | $0.00026 | $0.00324 |
| Sonnet 5 | $0.00010 | $0.00130 |
| Haiku 4.5 | $0.00005 | $0.00065 |
Grade A, and why
delegation-strategy 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegation Strategy
Core Rule
Delegate ONLY when the task needs a specialized tool/data source (web, email/calendar, IoT, finance, media). Reply directly for chitchat, venting, advice, opinions, or general Q&A — these are NOT delegation targets. Among delegations: use existing agents first, spawn new only when no existing agent fits.
Decision Flow
- Ambiguous / underspecified? → Ask the user to clarify the expected output FIRST. Then plan and pick: single agent, multiple agents, or an existing team template (
list_team_templates_tool→spawn_team_tool). - Existing agent matches? → Use
agent__<Name>tool directly - No match, short task (<2 min)? →
spawn_and_run_isolated - No match, long task? →
spawn_and_run_background
Existing Agents
| Agent | Domain |
|---|---|
| ResearchAgent | Web search, news, information synthesis |
| FinanceAgent | Stock prices, gold, crypto, market analysis |
| PersonalAgent | Email, calendar events, reminders (cron) — task management only, NOT casual conversation |
| CrawlStoriesAgent | Story crawling from web |
| IoTAgent | Smart home device control |
| MusicAgent | Music search and playback |
| AudioReaderAgent | Story audio playback |
Note: PersonalAgent uses the cron scheduler for reminders, NOT Google Calendar. Google Calendar is only for real events / meetings.
Spawn Tool Quick Reference
spawn_and_run_isolated(
task="...", # Specific task description
instruction="...", # Agent role and behavior
servers="serpapi, scrapling-server", # Comma-separated
skills="research, scrape-web", # Comma-separated
role="researcher", # Label for tracking
timeout_seconds=90 # Default 120
)
For background: same params, use spawn_and_run_background, default timeout 600s.
Check status with check_spawn_status(run_id).
Choosing Servers and Skills
See SERVERS.md for MCP server catalog and selection rules. See SKILLS.md for skill catalog and pairing guidance.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 68 lines · 51 tokens per session scan A 4adead859376
delegation-strategy is a skill published in the GitHub repository omnigentx/jarvis (37 stars, last pushed 12d ago), licensed MIT. It adds 51 tokens to every session and 648 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…