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 abossenbroek/abossenbroek-claude-plugins --skill multi-agent-collaborationgit clone --depth 1 https://github.com/abossenbroek/abossenbroek-claude-pluginsWrote 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/abossenbroek/abossenbroek-claude-plugins/multi-agent-collaboration)<a href="https://agentmods.dev/skills/abossenbroek/abossenbroek-claude-plugins/multi-agent-collaboration"><img src="https://agentmods.dev/badge/skills/abossenbroek/abossenbroek-claude-plugins/multi-agent-collaboration/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/abossenbroek/abossenbroek-claude-plugins/multi-agent-collaboration"><img src="https://agentmods.dev/badge/skills/abossenbroek/abossenbroek-claude-plugins/multi-agent-collaboration.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00071 | $0.01251 |
| Opus 5 | $0.00036 | $0.00626 |
| Sonnet 5 | $0.00014 | $0.00250 |
| Haiku 4.5 | $0.00007 | $0.00125 |
Grade A, and why
Multi-Agent Collaboration 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 10d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Agent Collaboration
Overview
State-of-the-art patterns for context-efficient multi-agent systems. These patterns enable complex agent workflows while minimizing token overhead through strategic context engineering.
Research Foundation
- Google ADK: Context compilation pipelines and session management
- Anthropic: Multi-agent coordination and handoff protocols
- Progressive Disclosure: Agent-readable semantic interfaces
- LangGraph/CrewAI/AutoGen: Framework-specific orchestration patterns
Pattern Selection Framework
| Pattern | Use When | Trade-offs |
|---|---|---|
| Hierarchical | Clear decomposition, audit trails | Central bottleneck, sequential latency |
| Swarm | Parallel exploration, diverse perspectives | Coordination overhead, emergent behavior |
| ReAct | Dynamic adaptation, tool-heavy workflows | Myopic decisions, may meander |
| Plan-Execute | Clear sequence, predictability needed | Less adaptive, requires replanning |
| Reflection | Quality refinement, self-correction | Added latency, may reinforce errors |
| Hybrid | Multiple coordination needs | Implementation complexity |
For detailed YAML definitions and examples of each pattern, see references/patterns.md.
The Four Laws of Context Management
Law 1: Selective Projection
Pass only fields each agent needs, not full data structures.
# BAD: Full snapshot everywhere
snapshot: {...20KB...}
# GOOD: Selective projection
context:
mode: deep
claims_analyzed: 15
high_risk_count: 4
Law 2: Tiered Context Fidelity
Define explicit tiers based on agent role:
| Tier | Description | Example Agent |
|---|---|---|
| FULL | Complete data | Initial analyzer |
| SELECTIVE | Relevant subset | Domain workers |
| FILTERED | Criteria-matched | Validators |
| MINIMAL | Mode + counts | Strategy/routing |
| METADATA | Scope stats only | Report synthesis |
Law 3: Reference vs Embedding
For large data, pass reference instead of full structure:
What ships with it
3 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.
- 10d ago First seen · 208 lines · 71 tokens per session scan A de68f420f8cf
Multi-Agent Collaboration is a skill published in the GitHub repository abossenbroek/abossenbroek-claude-plugins (2 stars, last pushed 4mo ago), licensed BSD-3-Clause. It adds 71 tokens to every session and 1,251 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 2026-08-31.
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…