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 fabioc-aloha/Alex_Skill_Mall --skill multi-agent-patternsgit clone --depth 1 https://github.com/fabioc-aloha/Alex_Skill_MallWrote 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/fabioc-aloha/alex_skill_mall/multi-agent-patterns)<a href="https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/multi-agent-patterns"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/multi-agent-patterns.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 5.1 | $0.00042 | $0.03369 |
| Opus 5 | $0.00021 | $0.01684 |
| Sonnet 5 | $0.00008 | $0.00674 |
| Haiku 4.5 | $0.00004 | $0.00337 |
Grade A, and why
multi-agent-patterns 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 4d 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.
This is a copy
98% identical to multi-agent-patterns — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Agent Architecture Patterns
Multi-agent architectures distribute work across multiple language model instances, each with its own context window. When designed well, this distribution enables capabilities beyond single-agent limits. When designed poorly, it introduces coordination overhead that negates benefits. The critical insight is that sub-agents exist primarily to isolate context, not to anthropomorphize role division.
When to Activate
Activate this skill when:
- Single-agent context limits constrain task complexity
- Tasks decompose naturally into parallel subtasks
- Different subtasks require different tool sets or system prompts
- Building systems that must handle multiple domains simultaneously
- Scaling agent capabilities beyond single-context limits
- Designing production agent systems with multiple specialized components
Do not activate this skill for adjacent work owned by other skills:
- Deciding task-model fit, pipeline shape, or project-level cost before topology is known:
project-development. - Designing hosted sandboxes, warm pools, remote sessions, or background runtime infrastructure:
hosted-agents. - Sharing orchestrator state through KV-cache compaction in controlled runtimes:
latent-briefing. - Designing the tools each agent exposes:
tool-design.
Core Concepts
Use multi-agent patterns when a single agent's context window cannot hold all task-relevant information. Context isolation is the primary benefit — each agent operates in a clean context without accumulated noise from other subtasks, preventing the telephone game problem where information degrades through repeated summarization.
Choose among three dominant patterns based on coordination needs, not organizational metaphor:
- Supervisor/orchestrator — Use for centralized control when tasks have clear decomposition and human oversight matters. A single coordinator delegates to specialists and synthesizes results.
- Peer-to-peer/swarm — Use for flexible exploration when rigid planning is counterproductive. Any agent can transfer control to any other through explicit handoff mechanisms.
- Hierarchical — Use for large-scale projects with layered abstraction (strategy, planning, execution). Each layer operates at a different level of detail with its own context structure.
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.
- 4d ago First seen · 268 lines · 42 tokens per session scan A 321802c10029
multi-agent-patterns is a skill published in the GitHub repository fabioc-aloha/Alex_Skill_Mall (4 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 3,369 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to multi-agent-patterns, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
apply-change-leadership
Use when a manager's team is experiencing a significant organizational change — restructuring, strategy shift, leadership change, layoffs, or major process transition — and needs leadership that maintains team stability, preserves trust, and converts uncertainty into direction.
apply-cross-functional-leadership
Use when a manager needs to lead a project or initiative that depends on team members or stakeholders they do not formally manage — to build voluntary cooperation, alignment, and momentum across organizational boundaries through influence rather than authority.
apply-grow-coaching
Use when a manager wants to help a direct report solve a problem, develop a skill, or reach a goal through structured questioning rather than advice-giving — because telling people answers builds dependency while coaching builds self-sufficiency.
apply-upward-influence
Use when a manager needs to build an effective working relationship with their own manager, secure resources or decisions for their team, or influence organizational priorities without formal authority over the outcome.
build-psychological-safety
Use when a team leader wants to assess and improve the degree to which team members feel safe to speak up, admit mistakes, ask questions, and disagree — because psychological safety is the strongest predictor of team learning and high performance.
run-performance-improvement-plan
Use when a direct report has a documented pattern of performance falling below role expectations — after informal feedback has not produced sustained change — to create a structured, time-bound plan with clear success criteria before making a continuation decision.