agent-creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when configuring how a Hermes Agent spawns subagents - delegation.* keys (model, provider, max_spawn_depth, max_concurrent_children, reasoning_effort, timeouts), delegation.backend with the advanced-delegation plugin (model_map, profile_routes), manager/worker topologies and
Claude Code
$ npx -y skills add fusengine/claude-plugins --skill hermes-delegation --agent claude-code
Codex
$ npx skills add fusengine/claude-plugins --skill hermes-delegation -a codex -y
Cursor
$ npx skills add fusengine/claude-plugins --skill hermes-delegation -a cursor -y
Gemini CLI
$ npx skills add fusengine/claude-plugins --skill hermes-delegation -a gemini-cli -y
GitHub Copilot
$ npx skills add fusengine/claude-plugins --skill hermes-delegation -a github-copilot -y
OpenCode
$ npx skills add fusengine/claude-plugins --skill hermes-delegation -a opencode -y
Windsurf
$ npx skills add fusengine/claude-plugins --skill hermes-delegation -a windsurf -y
name: hermes-delegation description: Use when configuring how a Hermes Agent spawns subagents - delegation.* keys (model, provider, max_spawn_depth, max_concurrent_children, reasoning_effort, timeouts), delegation.backend with the advanced-delegation plugin (model_map, profile_routes), manager/worker topologies and their cost. Not for scheduled jobs (hermes-cron), separate long-lived agents on their own channels (hermes-core profiles, hermes-gateways), or approval policy (hermes-security). versions: hermes-agent: "0.23.0" user-invocable: false references: - references/delegation-keys.md - references/backends-advanced-delegation.md - references/topology-cost.md - references/templates/delegation-default.yaml - references/templates/delegation-model-map.yaml - references/templates/delegation-profile-routes.yaml related-skills: - hermes-core - hermes-cron - hermes-security - hermes-chief-of-staff
<objective> Configure Hermes Agent 0.23.0 subagent delegation (`delegate_task`): which model and provider children run on, how deep and how wide the tree may grow, how a manager spawns temporary workers, the v0.23.0 pluggable backends (`delegation.backend`, official `advanced-delegation` plugin with `model_map` and `profile_routes`), and what each choice costs. Flags every place where the docs and the source disagree so the reader sets the value explicitly. </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 | |----------|------| | Which `delegation.*` key, default, conflict | [delegation-keys.md](references/delegation-keys.md) | | Per-task model choice or "subagent as another profile" | [backends-advanced-delegation.md](references/backends-advanced-delegation.md) | | Manager -> workers design, depth, spend | [topology-cost.md](references/topology-cost.md) | | Copy-paste config | [templates/](references/templates/) |
1. **Subagents know nothing.** Each child starts a fresh conversation with only the `goal` and `context` the parent writes, plus the workspace project context file (`.hermes.md` > AGENTS.md > ...). **SOUL.md is excluded.** 2. **Default is flat.** `delegation.max_spawn_depth` defaults to `1`: children are leaves and cannot delegate. One level (manager -> temporary workers) is the recommended pattern. 3. **Set limits explicitly.** `max_concurrent_children` is 10 in code and in `features/delegation.md`, but 3 in `configuration.md`; `max_spawn_depth` has no ceiling in code but "1-3, clamped" in `configuration.md` and the example file. Write the values you want. 4. **`delegation.reasoning_effort` is code-only** (present in `tools/delegate_tool_config.py`, undocumented). Use it, but say so, and verify with `hermes config get delegation.reasoning_effort`. 5. **Backends fail closed.** A `delegation.backend` whose plugin is missing returns a tool error; no child starts on another route. 6. **`profile_routes` lends credentials.** A listed profile's keys, SOUL.md and terminal policy are used by this profile's children. List only profiles you accept to share. 7. **Leaves cannot** call `delegate_task`, `clarify`, `memory`, `send_message`, `cronjob`. Both roles keep `execute_code`.
hermes config set delegation.model "<WORKER_MODEL_ID>" hermes config set delegation.provider "<PROVIDER>" hermes config set delegation.max_spawn_depth 1 hermes config set delegation.max_concurrent_children 10 hermes config get delegation.max_concurrent_children
Watch running children with `/agents` or Ctrl+T (classic CLI also F6), and their transcripts under `~/.hermes/cache/delegation/live/` (kept 7 days).
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.