Guide the addition of a new model generation to oh-my-hermes. The workflow checks model recognition, official specifications, routing rules that select models for tasks, documented pricing, and live access, then validates changes with tests and comparative benchmarks.
Onboard a new model generation or sibling into oh-my-hermes: probe router recognition, research the official contract, write trait-to-counter calibration, place routing in both lanes, price from documented list only, gate machine config on a served route, prove with the gates, close with a benchmark pair. Use when a model family ships a new generation (for example "Fable 5.1 is out", "GLM 5.4 shipped", "onboard new model", "add model to chains").
Review the instructions the agent will receive before you install.
The procedure lives in docs/MODEL-ONBOARDING.md.
Read that file and follow it in order.
It is kept there rather than here because Codex, Hermes handoffs, and generic
executor profiles run the same loop, and AGENTS.md requires that no single
executor own a shared surface. This file exists so the loop is reachable as
/model-onboarding; it holds no rules of its own.
Start by reading, in this order:
cat docs/MODEL-ONBOARDING.md
cat MODEL_OPTI.md
Nine things the loop gets wrong most often:
omh coding model-route first; a model_family of unknown
means the calibration never attaches. Probe the dated snapshot form too
(<id>-YYYY-MM-DD): some providers serve only that spelling, and it must
resolve the base's contract, chain position, price, and HUD label through
dated_snapshot_base() rather than falling to generic.deepseek-flash and 400s deepseek-v4.1-flash;
the versioned contract sits behind the pointer as a declared projection
and in EXACT_CONTRACT_POINTER_ALIASES..omc/research/; the Hermes lane is the one that
shows what the wire carries (id folding, effort overrides, passback).model-setup skill text, seven public doc surfaces,
the release budget note, and the pinned-chain tests all name the old id;
grep src/ tests/ docs/ README* site/ for it and move every site in the
same commit. Superseded generations leave the shipped chains (owner
decision, 2026-09-11) and join the recognition-only list; pins hide in
fixtures, so start the full suite in the background at the chain edit.model-providers.json. Place the id
with omh model-chains set, never by hand-editing the JSON; an operator
may keep an older generation behind it there, the shipped table does not.hermes --oneshot call
and read the usage file (model, provider, cost_status) before any
measurement or placement; gateways want the vendor-prefixed id.family arm next to baseline and optimized; expect pass rate to tie
and read the paired token delta, tool calls, and turns. Same pass with
more tokens on the tasks it fails is a sentence that pushes — cut it.-pro / -fast /
-flex aliases label their base id; self-review did not.Arguments pass through verbatim: the model ids as served (for example
claude-fable-5-1 claude-mythos-5-1).
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Coordinate a large job by splitting it into small tasks with explicit dependencies. Run ready tasks in parallel through Hermes, verify the combined result separately, and repair failures within defined limits before reporting completed work and remaining gaps.
Prepare an accessibility audit for an interface using WCAG 2.2 AA, an accessibility standard. Organize evidence for keyboard use, screen readers, contrast, target size, and zoom behavior, then document findings, missing checks, and remediation handoffs.
Summarize earned badges, recent unlocks, achievement tiers, and progress using local files from the hermes-achievements plugin. Prepare a badge list or report section while making missing information and the limits of the recorded snapshot clear.
Examine a technical proposal through independent perspectives, challenge their findings, and resolve objections. The result is a structured set of constraints, decisions, risks, and open questions for a separate planning workflow.
Coordinate multiple Hermes agents or profiles through a shared task board. Organize assignments, handoffs, activity updates, blockers, and completion states, while distinguishing planned actions from work supported by observed results.
Investigate an AI agent that stalls, repeats tool calls, or loses its goal. Compare possible causes against recorded evidence and prepare a small, reversible recovery step, with unresolved questions clearly identified.