CLAUDE

A document describing ways to coordinate specialized coding agents, such as planners, developers, reviewers, and documentation writers.

In plain words
What is it for?
Use it as a reference when assigning project management, architecture, backend, frontend, testing, documentation, refactoring, or Git work.
Why use it?
It provides repeatable role-based workflows for larger software changes and review tasks.

Agent

Install

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.

agentmods
npx agentmods add agents/bwads001/claude-code-agents/claude
Clone the repo
git clone --depth 1 https://github.com/bwads001/claude-code-agents
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,663 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01663
Opus 5 $0.00000 $0.00831
Sonnet 5 $0.00000 $0.00333
Haiku 4.5 $0.00000 $0.00166

Measured 3d ago against content hash 45b83d58a8c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CLAUDE 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.

agents/CLAUDE.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Agent Orchestration Patterns

This document contains orchestration patterns for working with specialized agents. These patterns should be used by the main Claude instance when coordinating development tasks.

Agent Orchestration Workflow

When implementing features or fixes, follow these orchestration patterns to effectively utilize specialized agents:

Available Agents and Their Roles

  • project-manager: Planning documentation management, project state tracking, context maintenance
  • feature-architect-planner: Comprehensive implementation planning for complex features
  • backend-database-engineer: Database schema, migrations, API routes, server logic
  • frontend-ui-specialist: UI components, styling, responsive design, accessibility
  • code-quality-reviewer: Code review, testing, quality gates, manual QA
  • documentation-specialist: Library research, technical documentation, knowledge management
  • file-refactor-organizer: Breaking down large files (>300 lines), code organization
  • git-workflow-specialist: Branch management, worktrees, commit hygiene

Orchestration Patterns

Complete Feature Implementation Workflow
🚀 START-OF-WORK (project-manager):
1. Use project-manager to move plan from backlog → active
2. Use project-manager to validate requirements and acceptance criteria
3. Use feature-architect-planner if implementation plan is missing

🔧 IMPLEMENTATION PHASE:
4. Use documentation-specialist to research new libraries/patterns
5. Use git-workflow-specialist to create feature branch/worktree
6. Use backend-database-engineer for schema changes and APIs
7. Use frontend-ui-specialist for UI components
8. Use file-refactor-organizer if files exceed 300 lines

✅ END-OF-WORK (project-manager orchestrated):
9. Use code-quality-reviewer for comprehensive testing and validation
10. Use project-manager to verify QA completion and acceptance criteria
11. Use git-workflow-specialist for commits, push, and PR creation
12. Use project-manager to move plan from active → completed → archived
13. Use project-manager to coordinate human code review readiness

Read the full file on GitHub · 193 lines

Changes

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.

  1. 3d ago First seen · 193 lines · 0 tokens per session scan A 45b83d58a8c9

Subscribe to this mod's changes

CLAUDE 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 1,663 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.