oh-my-hermes skill
operational skill layer over Hermes Agent and other harnesses: planning, project memory, and explicit evidence boundaries
- 5,520 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Installs scripts into configuration directories of multiple agents and changes their behavior
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/oh-my-hermesDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Installs scripts into configuration directories of multiple agents and changes their behavior
This is third-party code. Review the repository files before installing.
What it does
oh-my-hermes (OMH) installs on top of Hermes Agent and adds a professional operational layer: it turns a simple request into a clear task definition, selects the appropriate workflow, and requires explicit evidence of completed work instead of claims. It includes a set of ready-made skills, such as model onboarding or comprehensive change review (triage-sweep, review-sweep). The installer places files in the Hermes directory as well as in .claude, .codex, .cursor, and .opencode folders, allowing the same operational layer to be connected to other agents that support the SKILL.md format.
Who it is for. For Hermes Agent users who need structured planning and verifiable results rather than just dialogue.
Good fit when
- You need requests to first become tasks with a plan instead of running randomly
- You need project memory between sessions and explicit boundaries of what is confirmed by evidence
- You want the same operational skill layer in Claude Code, Codex, Cursor, or opencode
Not a fit when
- You only need plain Hermes Agent without an additional operational layer
- Tasks are simple and one-off where planning and evidence are unnecessary
Example request
Perform a triage-sweep on these changes and create a task with a plan before executionLimitations
The main scenario and terminology are built around Hermes Agent by Nous Research; integration with other agents via .claude, .codex, .cursor, and .opencode is described separately and may be less refined.
How to disable. Remove the installed files from the agent directories (.claude/skills, .codex, .cursor, .opencode, and the Hermes folder) as described in docs/INSTALLATION.md.
FAQ
Does OMH replace Hermes Agent itself?
No, the README clearly states that OMH does not replace or hide the code executor but adds an operational layer on top of the existing workflow.
Does it only work with Hermes?
The main scenario is Hermes Agent, but the installer also places files in .claude, .codex, .cursor, and .opencode directories for other harnesses.
Discussion
No questions or reviews yet.
Related
SkillsBrooklyn skills: 25 portable agent skills for pull requests, triage, cleanup, UI checks and research
A set of 71 skills for 1C:Enterprise covering configurations, extensions, forms, data composition schemas and roles, for Hermes Agent
Agent Harness Kit: structured agent workflow
Agent Harness Kit
The ahk CLI sets up five agent roles, a task MCP server and spec skills in your project for Claude Code, Codex and Cursor
pstack skill catalog ported to OMP: a task router, TDD, code review and subagent playbooks, each invoked by its own command.
iuhoay/skills collects agent skills: Vanilla Rails, Linear, stacked pull requests, plan challenging and tidy changes.
Gives each coding agent its own repository copy with separate ports and a database, then verifies results in one shared pipeline.
README in short
The README presents oh-my-hermes as a professional operational layer over Hermes Agent that turns requests into clear tasks, selects workflows, and requires explicit evidence boundaries instead of claims. Installation is done with a single command via install.sh or install.ps1, or directly by prompting the agent with commit SHA verification before executing instructions from the repository. Documentation is divided into installation, feature list, impact on results, and a separate guide for agent setup.