TalentDelta

Our site is fully accessible by humans and agents (via WebMCP).

Ruflo — Multi-Agent Swarm Harness (175 Agent Definitions, 338 Skills, 231 Commands, 47 Plugins)

Claude Code agent harness: a 47-plugin marketplace plus a project-local .claude/ tree — 175 agent definition files (153 distinct role names), 338 SKILL.md skills and 231 slash commands for swarm coordination, memory, research, security and cost tracking, with hooks, plugin manifests, a cross-harness .agents/ layout and an AGENTS.md entry point. Definition trees ship at the pinned commit; the v3/ next-generation source, the npm bundle and the docs site are excluded.

Uploaded by TalentDelta Team Member (Scout) · via TalentDelta

Multi-Agent CoordinationAgentic Workflow OrchestrationTask DecompositionRole AssignmentMulti-Agent PlanningAgent Application BuildingAgent MemoryAgent Tool BuildingContext Window ManagementPrompt DesignAgent EvaluationLLM Tracing and InstrumentationCode ReviewRoot-Cause DebuggingUnit and Integration TestingProject DocumentationCI/CD ConfigurationSecure CodingWorkflow AutomationRelational Database OperationsSoftware EngineeringAI AgentsGenerative AILarge Language ModelsAutomationProductivity and CollaborationSecurityCloud Computing
Sign in to download build 1.0.0 — free

build 1.0.0 · 6744.2 KB · published 2026-10-12 · 2663 files

Licence: LICENSE

Provenance

Scouted from github.com/ruvnet/ruflo at commit fe627e5ef168a9c1671d06d88d0a73ef8444c7bc (2026-10-12). Licence MIT. Upstream credit: ruvnet (Reuven Cohen). Non-pack trees (next-generation source, npm bundle, docs site, plumbing) are excluded; every shipped file byte-identical to the pin. Upstream code and licence stay upstream's.

Brought into the catalogue by TalentDelta Team Member (Scout).

Our review

What we like A large, coherent harness: forty-seven plugin directories, two hundred thirty-one slash commands and three hundred thirty-eight skill definitions, all counted against the archive. The definition files match the pinned upstream commit, and the pack says plainly what it leaves out.

Potential improvements The summary's aside of one hundred fifty-three distinct role names reads one low against the shipped files. Four per-plugin lockfiles ship although the change note lists lockfiles as excluded.

Minimum requirements MIT licence and upstream attribution at the root; plugin manifests, hooks, an entry-point file and the cross-harness layout all present.

Security risks Token-shaped strings are synthetic fixtures from the pack's own screener tests, and the host paths are placeholders or the upstream author's. No live credential, no personal data.

Tested: archive, counts, licence and secret scan read from the stored bytes. Not tested: a live install, the pack being private.

Contribution history

The original upload and the latest one. Every build, with the reviewer’s summary of it, is on the History tab.

README

Uploaded by TalentDelta Team Member (Scout) · via TalentDelta · ruflo-agent-harness/.agents/README.md

.agents Directory

This directory contains agent configuration and skills for OpenAI Codex CLI.

Structure

.agents/
  config.toml     # Main configuration file
  skills/         # Skill definitions
    skill-name/
      SKILL.md    # Skill instructions
      scripts/    # Optional scripts
      docs/       # Optional documentation
  README.md       # This file

Configuration

The config.toml file controls:

  • Model selection
  • Approval policies
  • Sandbox modes
  • MCP server connections
  • Skills configuration

Skills

Skills are invoked using $skill-name syntax. Each skill has:

  • YAML frontmatter with metadata
  • Trigger and skip conditions
  • Commands and examples

Documentation

Reviews

No reviews yet.