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
rlaope/oh-my-hermes
oh-my-hermes (OMH) sits above Hermes Agent as an operating layer rather than a replacement runtime. It takes an ordinary natural-language request, frames it as a specific capability, picks a workflow and the evidence gates that workflow requires, and then runs Hermes-native skills as capabilities inside that governed path. The stated aim is to turn a request into a clear capability, a useful next step and an honest record of what actually happened, keeping Hermes as the natural-language surface and never hiding a separate coding executor behind it. The core is a set of eleven ulw- workflows spanning planning, research, creation, coding handoffs, operations and project memory; saying the trigger phrase in chat routes the request to the right one, and a full catalog lives in the repository workflow reference. Because the workflows install into Hermes itself, they work identically across the Hermes desktop application, the CLI and the messenger frontend, with a thread-based run reporting its result back into the same thread. Installation offers several paths: a shell installer script on Unix systems or a PowerShell equivalent on Windows followed by an omh setup command that installs the workflows and connects them to Hermes; the Hermes skill tap route using hermes skills tap add and hermes skills install; or simply handing the repository URL to an agent. Maintenance commands cover updating and a doctor health check, and the documentation covers reconciling a full install back to the core set. Documentation is available in English, Korean, Japanese and Chinese, and the project ships a documentation site, a capabilities reference and a capability impact document. The emphasis throughout is on explicit evidence boundaries: each workflow states what it verified and what it did not, so the record of a run can be audited rather than taken on trust.
https://github.com/rlaope/oh-my-hermes
Also in Commands & Workflows
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.
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.