Ruflo is an execution and coordination layer for Claude Code and Codex that equips AI coding agents with tools, memory, control loops, sandboxes, and collaboration mechanisms. Developers use it to organize specialized agents into swarms, coordinate workflows, retain knowledge across sessions, and communicate across machines. The catalogue entries are Ruflo’s skills, commands, agents, hooks, and plugin components.
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/ruvnet/ruflo/agent-typesgit clone --depth 1 https://github.com/ruvnet/rufloWrote 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/ruvnet/ruflo/agent-types)<a href="https://agentmods.dev/agents/ruvnet/ruflo/agent-types"><img src="https://agentmods.dev/badge/agents/ruvnet/ruflo/agent-types.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 | $0.00170 |
| Opus 5 | $0.00000 | $0.00085 |
| Sonnet 5 | $0.00000 | $0.00034 |
| Haiku 4.5 | $0.00000 | $0.00017 |
Grade A, and why
agent-types 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 yesterday.
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.
Copies of this mod
8 near-identical copies found in the catalogue:
- agent-types — 100% identical, 0 lines differ
- agent-types — 100% identical, 4 lines differ
- agent-types — 100% identical, 0 lines differ
- agent-types — 100% identical, 0 lines differ
- agent-types — 100% identical, 0 lines differ
- agent-types — 100% identical, 0 lines differ
- agent-types — 100% identical, 0 lines differ
- agent-types — 100% identical, 0 lines differ
What it actually says
agent-types
Complete guide to all 54 available agent types in Claude Flow.
Core Development Agents
coder- Implementation specialistreviewer- Code quality assurancetester- Test creation and validationplanner- Strategic planningresearcher- Information gathering
Swarm Coordination Agents
hierarchical-coordinator- Queen-led coordinationmesh-coordinator- Peer-to-peer networksadaptive-coordinator- Dynamic topology
Specialized Agents
backend-dev- API developmentmobile-dev- React Native developmentml-developer- Machine learningsystem-architect- High-level design
For full list and details:
npx claude-flow agents list
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.
- yesterday First seen · 27 lines · 0 tokens per session scan A d791bef16a13
agent-types is an agent published in the GitHub repository ruvnet/ruflo (70,498 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 170 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 2026-09-03.
Other agents, from other repositories
nw-software-crafter
DELIVER wave - SLIM scope (implementation + refactor expert). Crafter implements production code to satisfy ATs authored by acceptance-designer (DISTILL). Does NOT author tests. Follows the 3-phase RED -> GREEN -> COMMIT cycle (ADR-025).
nw-solution-architect
Use for DESIGN wave - collaborates with user to define system architecture, component boundaries, technology selection, and creates architecture documents with business value focus. Hands off to acceptance-designer.
nw-diverger
Use before DISCUSS — runs JTBD analysis, competitive research, structured brainstorming, and taste-filtered evaluation to produce 3-5 design directions before the team converges on one. Use when the team has a validated problem but hasn't chosen a solution approach.
nw-product-discoverer
Conducts evidence-based product discovery through customer interviews, assumption testing, and opportunity validation. Use when validating problems exist, prioritizing opportunities, or confirming market viability before writing requirements.
nw-skill-reviewer
Use to review SKILL.md quality during DISTILL/DELIVER verification when deliverabletype is plugin or skill. Validates skill structure, scope discipline, frontmatter, and domain-knowledge quality. Thin reviewer — reuses nw-agent-builder skill assets. Runs on Haiku for cost efficiency.
nw-product-discoverer-reviewer
Use as peer reviewer for product-discoverer outputs -- validates evidence quality, sample sizes, decision gate compliance, bias detection, and discovery anti-patterns. Runs on Haiku for cost efficiency.