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
mrrkrieg/loopgraph
Loopgraph gives Hermes Agent a versioned operating model of a company: recurring business processes are described as department-owned loops, and verified events are routed into them by the model while a deterministic layer decides whether the route is allowed. The split is deliberate. A connector broker verifies provider events, keeps credentials out of the model's reach, runs leased bounded detectors for sources without webhooks, normalises payloads and exposes only capability-scoped provider operations. Hermes then determines what business problem occurred, which company object is affected, whether this is a new problem or more evidence for an existing one, which loops claim that problem type, which of them hold the required context and active connections, and whether exclusions, risk rules or human ownership apply — or whether it should abstain and ask for a human. Loopgraph independently confirms that the proposed route exists, accepts the event, has the required evidence, is active and is permitted to run, then records execution and evaluates whether the work produced a measurable outcome, feeding that evidence back into later routing and loop-improvement decisions. A live topology view renders the graph as Hermes Brain to Department to Loop with an inspector for the selected node. The repository ships a dependency-free native Hermes adapter under `integrations/hermes-plugin`, installed on its own so Hermes scans only the plugin boundary rather than the full application source; it declares a `pre_llm_call` hook, bundles design and event-router skills, and adds `hermes loopgraph plan` and `hermes loopgraph install` commands. The plan command is read-only and prints the exact Git commit and package-lock digest; installation fetches that immutable revision into plugin-owned runtime storage, refuses a different lockfile, installs dependencies with lifecycle scripts disabled, requires a clean production audit and registers restricted MCP profiles. Provider credentials are never accepted or stored by the plugin, and disconnecting removes only the MCP registrations. TypeScript core, MIT licensed.
https://github.com/mrrkrieg/loopgraph
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.
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.
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.