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
Lifecycle-Innovations-Limited/claude-ops
claude-ops packages day-to-day business operations as a plugin that runs across three harnesses, Claude Code, Grok and Hermes Agent. A single command produces a morning briefing that puts infrastructure health, CI/CD status, a unified inbox across Slack, Telegram and Gmail, open pull requests, sprint progress and a revenue snapshot from Stripe, RevenueCat and AWS on one screen, and closes with a suggested next action. The Hermes port lives in `claude-ops/hermes-plugin/`, a directory holding the Hermes manifest, a Python entry point and its own runtime notes, installed to `~/.hermes/plugins/ops`. It exposes the plugin's slash commands and makes the bundled skills reachable through `skill_view("ops:*")`. Version numbers in `plugin.json`, the Hermes `plugin.yaml` and the installer pin are kept in step by a release skill, and the plugin's `.mcp.json` is deliberately empty so MCP servers start on demand rather than once per session. A separate document records what each harness port does and does not support. Beyond the briefing the repository bundles a large content set: dozens of skills, a set of agents, and integrations with external services. The second major version added an autonomy layer on top of the reporting surface, including post-merge and build-failure auto-fix, plus safety hooks; the project describes those additions as purely additive, with no change to earlier behaviour unless enabled. Skills use third-person trigger descriptions and a shared preamble, and oversized ones are split into `references/` files, with a plugin-root rules skill acting as the single source of project conventions. The repository is mostly shell and documentation, and the Hermes plugin is a port of a code base whose primary target is Claude Code. Anyone adopting it on Hermes should read the harness ports document first to see which surfaces are wired through and which stay Claude-only.
https://github.com/Lifecycle-Innovations-Limited/claude-ops
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.
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.
yuzushi-dev/hermes-seo
Native Hermes Agent port of the Claude SEO toolkit: 25 workflow skills, 19 specialist role skills and 56 scripts for site audits, schema validation and SEO planning.
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.
August06exe/ai-landing-consultant
An open-source "landing consultant" playbook of 11 SOPs, compliance-aware skills, and a Hermes plugin shell that turns a fresh agent into a client's self-assembling AI assistant.
100yenadmin/hermes-plan-mode
Hermes Agent plugin that turns /plan into an enforced read-only-explore, approve, then-implement workflow with approval cards on every interactive Hermes surface.
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.