OthmanAdi/planning-with-files
This repository provides a persistent, file-based planning skill for AI coding agents, ensuring plans survive context loss, restarts, and offering a completion gate for long-running tasks.
Awesome Hermes Plugins › Commands & Workflows
obra/superpowers
Superpowers packages a software development methodology as a set of composable agent skills plus bootstrap instructions that make the agent reach for them automatically. Instead of writing code on the first request, the agent brainstorms the requirement, extracts a specification in reviewable chunks, produces an implementation plan aimed at an inexperienced engineer with no project context, and only then starts work. Execution runs through subagent-driven development: a fresh subagent per task, two-stage review for specification compliance and then code quality, and enforced red-green-refactor test-driven development with YAGNI and DRY as explicit constraints. Long autonomous runs are the intended mode, with the plan rather than the conversation holding the state. The repository ships installers for many agent harnesses, among them Claude Code, Codex, Cursor, Gemini CLI, Copilot CLI, OpenCode, Devin, Factory Droid, Antigravity, Kimi Code and Pi, and it includes a Hermes Agent plugin under a .hermes-plugin directory with a manifest and a Python entry point. On Hermes it installs with hermes plugins install obra/superpowers --enable and registers the using-superpowers bootstrap so that the skills trigger without being named. The README notes a Hermes limitation: there is no post-compaction hook, so a session that compacts over its first turn loses the bootstrap and needs restarting. Beyond the core workflow the bundle carries skills for git worktree isolation, plan writing, batched execution with human checkpoints, and review. It is aimed at engineers who want a coding agent to follow a repeatable process rather than improvise per request, and at teams standardising that process across several agent tools. Commercial support is offered separately by the maintainers.
https://github.com/obra/superpowers
Also in Commands & Workflows
rlaope/oh-my-hermes
Operating layer for Hermes Agent that adds eleven routed workflows covering planning, research, creation, coding handoffs, operations and project memory with explicit evidence boundaries.
Lifecycle-Innovations-Limited/claude-ops
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.
lingjiuu/hermes-dynamic-workflows
This plugin introduces dynamic workflows to Hermes Agent, allowing models to write, execute, and orchestrate sandboxed Python scripts for complex multi-agent tasks.
xuyang-liu16/hermes-code-bridge
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.
Bergschloss/Refine-Cycle-for-Hermes-Agent
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.
mrrkrieg/loopgraph
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.
MahdiHedhli/HermesUltraCode
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.