obra/superpowers
A composable skill and workflow bundle, installable as a Hermes plugin, that drives coding agents through brainstorming, specification, planning, red-green-refactor TDD and subagent-driven implementation.
Awesome Hermes Plugins › Commands & Workflows
Planning-with-Files is a robust skill designed for AI coding agents, offering persistent, disk-based planning capabilities. It addresses critical challenges in agentic AI development, such as context loss and system crashes, by writing planning artifacts like `task_plan.md`, `findings.md`, and `progress.md` directly to disk. This ensures that an AI agent can recover its state and continue its work even after interruptions, making it highly suitable for long-running agentic tasks. The skill also introduces an opt-in completion gate, holding the agent until its plan is genuinely finished. The project emphasizes its compatibility with a wide array of agents, installing across 60+ platforms via the SKILL.md standard, and explicitly mentions support for agents like Claude Code, Codex CLI, Cursor, Kiro, and OpenCode. It takes inspiration from the Manus approach to AI planning, which focuses on reliable, file-centric state management. The repository provides detailed release notes, highlighting ongoing improvements in compatibility (e.g., Codex hooks on Windows), robustness, and new features like per-invocation opt-out for planning. It also showcases community contributions, including forks that extend its functionality for multi-project support, interview workflows, and multi-level task orchestration, demonstrating its utility and adaptability within the AI agent ecosystem.
https://github.com/OthmanAdi/planning-with-files
A composable skill and workflow bundle, installable as a Hermes plugin, that drives coding agents through brainstorming, specification, planning, red-green-refactor TDD and subagent-driven implementation.
Operating layer for Hermes Agent that adds eleven routed workflows covering planning, research, creation, coding handoffs, operations and project memory with explicit evidence boundaries.
A business operations plugin that ports to Hermes Agent, gathering infrastructure health, CI/CD, inbox, pull requests, sprint state and revenue into one briefing plus autonomous agents.
This plugin introduces dynamic workflows to Hermes Agent, allowing models to write, execute, and orchestrate sandboxed Python scripts for complex multi-agent tasks.
This Hermes Agent plugin acts as a control plane, enabling coordination and routing of tasks to local coding agents like Codex, Kimi Code, Claude Code, OpenCode, and Gemini CLI.
Cross-session self-improvement plugin that fingerprints Hermes' repeating mistakes, writes a bounded lesson to memory or skills once a threshold is met, then grades whether it helped.
Native Hermes plugin and governance layer that routes verified company events into department-owned business loops, validating each routing decision, controlling execution and recording the outcome.
Hermes Agent plugin that gates every subagent dispatch behind a review by a model from a different lab, allowing only tightening or blocking, and records each decision in an immutable audit trail.