Menu
Route tasks to local Ollama models or cloud APIs based on triage output. Health-check aware with automatic cloud fallback.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Branch, commit, push, and open PRs with humanized messages, then monitor GitHub Actions CI. Per-project autonomy gating; blocks direct pushes to the default branch and pushes with a dirty tree. Never auto-merges.
Dispatch patterns for Claude Code as the coding engine. Default harness. Implementation dispatches go through dispatch_coder.py (writes the dispatch receipt the commit gate requires).
Testing strategy, TDD enforcement, spec compliance, and regression checks.
Write implementation plans: bite-sized tasks for coding engine dispatch.
Automated fix loop for failed Quality/Reviewer checks. Parses failures, builds escalating prompts, dispatches through the active harness up to 3 times.
Run independent, file-disjoint plan tasks concurrently, each isolated in its own git worktree + branch. Collects per-task results; never auto-merges.
| name | local-model-router |
| description | Route tasks to local Ollama models or cloud APIs based on triage output. Health-check aware with automatic cloud fallback. |
| version | 1.0.0 |
| platforms | ["linux","macos","windows"] |
| metadata | {"hermes":{"tags":["routing","ollama","local-model","cloud","dispatch","cost-optimization"],"related_skills":["complexity-triage","humanizer-gate","skill-discovery"]}} |
Status: paused. Per the standing "no local models for now" directive (current machine too slow; revisit on capable hardware), do not route any work to local models. All dispatches and LLM-backed support passes go through the active cloud coding harness (
coding.default_engine, override with--engine). The routing logic below is retained for when local models are re-enabled; until then, treat every task as cloud-routed and ignorelocalrecommendations from triage.
Route coding tasks between local Ollama models and cloud APIs based on complexity triage results.
Before routing to local, always verify Ollama is healthy:
terminal(
command="python3 ~/.hermes-coder/scripts/ollama_manager.py health",
workdir="~/.hermes-coder",
timeout=10
)
Exit 0 = healthy, proceed with local routing. Exit 1 = unhealthy, route everything to cloud.
Local model routing applies to:
--api-base and -m flags)For claude-code dispatches, the model always uses Anthropic's cloud API. Triage output informs --max-turns and skill injection but does not change the model.
When larger models are added (gemma4:27b, qwen3-coder:30b), update:
config.yaml ollama.models section with new entrytriage.routing.local_sizes to include Mscripts/ollama_utils.py MODEL_REGISTRY with new capabilities