README

A guide to the sub-agents available for the ccswarm project. It lists specialists for frontend work, backend work, DevOps, testing, and code reviews.

In plain words
What is it for?
Use it to find agents for React or Vue interfaces, APIs and databases, Docker and deployment, testing, architecture reviews, and integrated project reviews.
Why use it?
It helps developers choose the right specialist for a task and understand how agents can work together in separate worktrees, which are isolated copies of the codebase.

Agent for Claude Code

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/nwiizo/ccswarm/readme
Clone the repo
git clone --depth 1 https://github.com/nwiizo/ccswarm

Made for: Claude Code.

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 790 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 $0.00790
Opus 5 $0.00000 $0.00395
Sonnet 5 $0.00000 $0.00158
Haiku 4.5 $0.00000 $0.00079

Measured 3d ago against content hash 6082df639c75, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

README 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.

.claude/agents/README.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Agents

Sub-agents for the ccswarm project. Designed for both individual invocation and Agent Teams parallel execution.

Agent Teams (Parallel Execution)

The 4 domain agents support Agent Teams for parallel multi-agent work:

claude --agent-team                          # Interactive team setup
claude --team "frontend-specialist" "backend-specialist" "qa-specialist"

Each domain agent has isolation: worktree — they work in independent git worktrees and communicate via @agent-name direct messaging.

Domain Agents (Agent Teams compatible)

Agent Model Isolation Focus
frontend-specialist sonnet worktree React, Vue, UI/UX, CSS
backend-specialist sonnet worktree APIs, databases, Rust server logic
devops-specialist sonnet worktree Docker, CI/CD, infrastructure
qa-specialist sonnet worktree Testing, quality, coverage

Review Agents (Subagent invocation)

Agent Model Skill Purpose
all-reviewer sonnet /review-all Integrated review (design, quality, architecture)
architecture-reviewer sonnet /review-architecture Architecture pattern compliance
rust-fix-agent opus Proactive Build/clippy error fixing (YAGNI)
code-refactor-agent opus /review-duplicates Duplicate detection and refactoring (DRY)
review-fix-agent opus /review-fix Review current changes, fix clear bugs, and verify

Usage

As Agent Team

# Start a team of frontend + backend + QA working in parallel
claude --team "frontend-specialist" "backend-specialist" "qa-specialist"

# Each agent gets its own worktree and context window
# Communicate between agents: @backend-specialist status?

As Individual Subagent

subagent_type: "rust-fix-agent"
prompt: "Fix all clippy warnings in crates/ccswarm/"

Via Skill

/review-all              # Triggers all-reviewer agent
/review-architecture     # Triggers architecture-reviewer agent
/review-duplicates       # Triggers code-refactor-agent
/review-fix              # Triggers review-fix-agent
/check-production-ready  # Triggers rust-fix-agent

Read the full file on GitHub · 83 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 · 83 lines · 0 tokens per session scan A 6082df639c75

Subscribe to this mod's changes

README is an agent published in the GitHub repository nwiizo/ccswarm (149 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 790 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 2026-08-30.