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
MahdiHedhli/HermesUltraCode
HermesUltraCode wraps the point at which Hermes Agent hands a task to a subagent. Before any worker starts writing code, the dispatched prompt goes to a neutral reviewer running on a different model lab than the orchestrator, a separation the plugin enforces at startup so a model cannot grade its own work and so the reviewer does not share the orchestrator training data or failure modes. The reviewer may only append constraints or block outright; it can never rewrite, delete, broaden or grant tool access, and the property that the dispatched prompt equals the base prompt verbatim plus directives is validated in code rather than trusted to the model. The release decision also lives in code: the dispatcher refuses to release until a structured, present, parseable, passing verdict exists, so no agent negotiates release in chat. The gate fails closed. A missing, late, garbled, unparseable or quota-starved verdict blocks and escalates rather than passing through, and with no reviewer configured every delegate_task is blocked instead of dispatching an un-vetted worker. Each dispatch writes one immutable, secret-redacted audit row; updates and deletes are blocked at the database level, and the trail exports to JSON and CSV. A vendored generation ruleset, ported from the Ponytail project, biases the orchestrator and workers toward minimal code while never touching the reviewer, and its carve-outs are extended for security and compliance material. The plugin ships a native UltraCode tab inside the Hermes web dashboard with sub-views for the live orchestrator and parallel subagents, the build plan and the audit trail including a visible fail-closed flag; the same views run as a build-free standalone dashboard. Work is driven with an /ultracode slash command. The core is standard library only with zero runtime dependencies and 208 offline tests that mock the model provider.
https://github.com/MahdiHedhli/HermesUltraCode
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.
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.