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/bwads001/claude-code-agents/multi-agent-system-overviewgit clone --depth 1 https://github.com/bwads001/claude-code-agentsWrote 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/bwads001/claude-code-agents/multi-agent-system-overview)<a href="https://agentmods.dev/agents/bwads001/claude-code-agents/multi-agent-system-overview"><img src="https://agentmods.dev/badge/agents/bwads001/claude-code-agents/multi-agent-system-overview.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 | $0.00000 | $0.01451 |
| Opus 5 | $0.00000 | $0.00726 |
| Sonnet 5 | $0.00000 | $0.00290 |
| Haiku 4.5 | $0.00000 | $0.00145 |
Grade A, and why
multi-agent-system-overview 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 3d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Agent Development System
This document provides a comprehensive overview of the specialized Claude Code agents and their orchestration patterns.
Agent Architecture
Our multi-agent system follows the orchestrator-worker pattern with the lead-developer-orchestrator coordinating specialized agents through explicit Task tool delegation.
Core Agents
| Agent | Purpose | Model | Key Capabilities |
|---|---|---|---|
lead-developer-orchestrator |
Project coordination & agent orchestration | Sonnet | Task delegation, quality gates, workflow coordination |
feature-architect-planner |
Feature planning & breakdown | Opus | Complex planning, ai-docs/planning integration, objective-based tasks |
backend-database-engineer |
Database & backend development | Sonnet | Schema design, migrations, Server Actions, API development |
frontend-ui-specialist |
UI/UX development & styling | Sonnet | React components, responsive design, QA feedback integration |
code-quality-reviewer |
Comprehensive code review & testing | Opus | Playwright testing, multi-device QA, accessibility validation |
file-refactor-organizer |
Code organization & refactoring | Sonnet | Breaking down large files, maintaining 300-line rule |
documentation-specialist |
Research & technical documentation | Opus | Context7 MCP research, ai-docs/ management, library integration guides |
git-workflow-specialist |
Git workflow & branch management | Sonnet | Feature branches, git worktrees, commit hygiene, parallel development |
Agent Orchestration Patterns
1. New Feature Implementation
1. feature-architect-planner → Create implementation plan in ai-docs/planning/active/
2. backend-database-engineer → Schema and backend services
3. frontend-ui-specialist → UI components and user interactions
4. code-quality-reviewer → Comprehensive review and testing
5. file-refactor-organizer → Clean up any files >300 lines
2. Library Integration Workflow
1. documentation-specialist → Research library and create ai-docs/ guide
2. feature-architect-planner → Plan integration approach
3. backend/frontend specialists → Implementation based on guide
4. code-quality-reviewer → Validate integration
5. documentation-specialist → Update patterns and lessons learned
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.
- 3d ago First seen · 145 lines · 0 tokens per session scan A cafedff8b33c
multi-agent-system-overview is an agent published in the GitHub repository bwads001/claude-code-agents (10 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,451 tokens. 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 agents, from other repositories
epic-summarizer
Distills a completed Epic (T2 Feature done) into a permanentmemory.md section. Captures architectural decisions, gotchas, anti-patterns, conflicts. Writes ONLY to .claude/memory/. Confidence-scored: items below 0.7 land in a Tentative subsection.
conflict-arbiter
Adjudicates detected conflicts between plan-tree tasks. Decides freeze | sequential | replan | escalate per spec §21.5. Read-only on code; writes only to .claude/plans/conflicts.jsonl + history.jsonl.
frontend
Frontend frameworks (React/Vue/Angular/Next.js), design systems, accessibility. Use for UI implementation, component work, and responsive design.
lead
Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.
replanner
Triggered by failure-classifier on F2-F4 escalations. Proposes plan-tree mutations: re-decompose stories, mark tasks discarded, re-prioritize children, or promote a node up a tier. Read-only on code; mutations applied via master-planner.
tester
Test strategy, automation, TDD enforcement, coverage analysis. Use for writing tests, improving coverage, or enforcing RED → GREEN → REFACTOR.