agent-creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when installing, updating, or configuring Nous Research Hermes Agent itself - install.sh, update channels, profiles and the multiplexed gateway, config.yaml keys, models/providers, SOUL.md / .hermes.md / AGENTS.md resolution, sessions and context resets, logs and health
Claude Code
$ npx -y skills add fusengine/claude-plugins --skill hermes-core --agent claude-code
Codex
$ npx skills add fusengine/claude-plugins --skill hermes-core -a codex -y
Cursor
$ npx skills add fusengine/claude-plugins --skill hermes-core -a cursor -y
Gemini CLI
$ npx skills add fusengine/claude-plugins --skill hermes-core -a gemini-cli -y
GitHub Copilot
$ npx skills add fusengine/claude-plugins --skill hermes-core -a github-copilot -y
OpenCode
$ npx skills add fusengine/claude-plugins --skill hermes-core -a opencode -y
Windsurf
$ npx skills add fusengine/claude-plugins --skill hermes-core -a windsurf -y
name: hermes-core description: Use when installing, updating, or configuring Nous Research Hermes Agent itself - install.sh, update channels, profiles and the multiplexed gateway, config.yaml keys, models/providers, SOUL.md / .hermes.md / AGENTS.md resolution, sessions and context resets, logs and health checks, release watching. Not for subagent settings (hermes-delegation), scheduled jobs (hermes-cron), messaging adapters (hermes-gateways) or approvals/sandbox (hermes-security). versions: hermes-agent: "0.23.0" user-invocable: false references: - references/install-update.md - references/profiles-gateway.md - references/config-schema.md - references/models-providers.md - references/persona-context-files.md - references/sessions-and-context.md - references/logs-health.md - references/release-watch.md - references/templates/config-core.yaml - references/templates/SOUL.md - references/templates/hermes-project.md - references/templates/freshness-check.sh related-skills: - hermes-delegation - hermes-cron - hermes-gateways - hermes-security - hermes-extend
<objective> Install, update and configure Nous Research Hermes Agent (open source, MIT, github.com/NousResearch/hermes-agent) at version 0.23.0 "The Hearth Release": the install script and update channels, profiles and the single multiplexed gateway, the real `config.yaml` keys with their defaults, model/provider selection, the identity and project-context files (SOUL.md, .hermes.md, AGENTS.md) and how they are resolved, session continuity after the retirement of idle/daily resets, logs and health checks, and how to detect a newer release. Every key written here was read in the official docs or source. </objective>
Before writing or changing any Hermes config, run `hermes --version` and `hermes update --check`, then read https://github.com/NousResearch/hermes-agent/releases/latest. If the installed or latest version is newer than 0.23.0, read every release note since 0.23.0 ("Upgrade notes" first) and adjust. Never apply guidance from this skill to a newer version without that check.
| Question | Load | |----------|------| | Install, first setup, update, channels, rollback | [install-update.md](references/install-update.md) | | Several agents on one machine, gateway processes | [profiles-gateway.md](references/profiles-gateway.md) | | Which `config.yaml` key, default, precedence, `hermes config` | [config-schema.md](references/config-schema.md) | | Choosing a model / provider / fallback / reasoning effort | [models-providers.md](references/models-providers.md) | | SOUL.md vs .hermes.md vs AGENTS.md, lookup order | [persona-context-files.md](references/persona-context-files.md) | | Fresh context, `/new`, session pruning, prompt refresh | [sessions-and-context.md](references/sessions-and-context.md) | | Something is broken: logs, doctor, status | [logs-health.md](references/logs-health.md) | | Is there a newer Hermes? What changed? | [release-watch.md](references/release-watch.md) | | Ready-to-fill files | [templates/](references/templates/) |
1. **Never invent a key.** Write only keys found in `cli-config.yaml.example`, `user-guide/configuration.md` or the source. After `hermes config set`, run `hermes config get <key>`: it prints a stderr notice when Hermes may not read the key. 2. **Secrets go in `.env`, never in `config.yaml`.** `hermes config set` routes every `UPPER_SNAKE` name to `.env` automatically. 3. **One profile = one Hermes home.** Two agent processes must not share one home; one profile per agent, deployed as a distribution (`hermes profile install <dir> --name <name> --yes --force`, hermes-deploy). 4. **Profiles are not sandboxes.** Set an absolute `terminal.cwd` per profile for a predictable workspace; isolation belongs to hermes-security. 5. **Fresh context is not automatic.** Idle/daily `session_reset` is ignored by core since v0.22.0; use `/new` or the catalog plugin `hermes-session-reset-policy`. 6. **SOUL.md lives only in `HERMES_HOME`**; project rules live in `.hermes.md` (walks up to the git root). Cron jobs load project rules only with `--workdir` (see hermes-cron). 7. **Docs disagree with code on some defaults** (e.g. delegation limits, `sessions.auto_prune`). When two official sources disagree, set the value explicitly instead of relying on the default.
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash # Linux/macOS/WSL2 source ~/.bashrc # or ~/.zshrc hermes setup # full wizard (or: hermes model, hermes tools, hermes gateway setup) hermes doctor # exit 1 while a problem remains hermes --version
Then edit config from [templates/config-core.yaml](references/templates/config-core.yaml) with `hermes config edit`, and validate with `hermes config check` + `hermes doctor`.
A plugin ecosystem that turns Claude Code into a supervised, multi-agent development environment.
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when starting ANY development task -- feature, bug fix, refactor, hotfix (triggers: implement, create, build, fix, add…
Use when creating a feature/component or adding functionality. Fires BEFORE APEX Analyze to refine requirements via structured…
Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches the owner (APEX or plain…
Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture…
Use when an expert agent self-reviews and self-corrects code after the Execute phase, before sniper validation (BMAD-METHOD…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.