model-routing

model-routing is a command for coding agents from JayOfemi/claude-harness-forge. It costs 21 tokens per session (759 once invoked), scanned B, original, MIT.

A command set for controlling how coding work is assigned to different AI model seats, such as exploration, planning, execution, and review.

In plain words
What is it for?
Use it to check routing, switch seats between automatic and inherited settings, or set a specific model for a work stage.
Why use it?
It removes the need to manually manage which model handles each stage. You can see the current assignments, let them follow session settings, or pin a stage to a chosen model.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/jayofemi/claude-harness-forge/model-routing
Clone the repo
git clone --depth 1 https://github.com/JayOfemi/claude-harness-forge

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for model-routing

README.md
[![agentmods](https://agentmods.dev/badge/commands/jayofemi/claude-harness-forge/model-routing.svg)](https://agentmods.dev/commands/jayofemi/claude-harness-forge/model-routing)
Your own site
<a href="https://agentmods.dev/commands/jayofemi/claude-harness-forge/model-routing"><img src="https://agentmods.dev/badge/commands/jayofemi/claude-harness-forge/model-routing.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 759 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.00759
Opus 5 $0.00010 $0.00380
Sonnet 5 $0.00004 $0.00152
Haiku 4.5 $0.00002 $0.00076

Measured 4d ago against content hash 02134665c2e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

model-routing scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Subtle steeringmediumPrompt injection

Instructions that bias recommendations or shape behaviour without the user noticing.

**status**: Read both values in all four files and report each seat (dynamic, or pinned to which model), the position (`dynamic` when every seat memory reads dynamic, `inherit` when all four live values read `inherit`, M
template/commands/model-routing.md · 23 lines

What it actually says

Operate the model-routing switch (STANDARDS/model-routing.md, "The adopted rails"). Routing is delegation-based: stage work goes to four subagents at ~/.claude/agents/: Explore.md, Plan.md, Execute.md, Review.md. Every seat is DYNAMIC by default, resolved when a spawn is about to happen: no seat ever runs above the session's own tier, Plan and Review ride the session tier exactly, Explore resolves to haiku (the floor), and Execute runs sonnet capped at the session tier (callers on stronger sessions pass model: sonnet at spawn). A pin set through this command overrides the dynamic rule for that seat, verbatim.

Each file carries the live model: value and the seat memory (<!-- Seat: X --> near the end of the body): dynamic, or a pinned model. A dynamic seat's live value is model: haiku for Explore and model: inherit for the other three.

$ARGUMENTS is one of status (default when empty), dynamic, inherit, or set <stage> <model|dynamic>.

status: Read both values in all four files and report each seat (dynamic, or pinned to which model), the position (dynamic when every seat memory reads dynamic, inherit when all four live values read inherit, MIXED otherwise), and what the dynamic seats resolve to for THIS session given its model. Change nothing. Never tell the user to change their session model; the switch reads it, never sets it.

dynamic: Resume routing per the seat memories with the Edit tool: a seat remembering dynamic gets its dynamic live value (Explore model: haiku, others model: inherit); a seat remembering a pin gets that pin back. Report what changed.

inherit: Routing off. Set all four live model: values to inherit, leaving every seat memory untouched (the memory is what a later dynamic restores). Every stage then follows the session model.

set <model|dynamic>: <stage> is one of explore, plan, execute, review. set <stage> dynamic returns that seat to the dynamic rule (memory dynamic, live value per the mapping above). set <stage> <model> with a model tier your harness accepts (for example haiku, sonnet, opus) pins the seat: update the memory, and unless the position is currently inherit, set the live value to match. Never accept inherit as a seat value; it is a position, not a seat. Reject anything else with the valid options. Warn once when pinning a premium tier: premium spawns run without an approval prompt, so the cost surfacing is the seat's own self-report line, after the fact. A pin is honored verbatim, even above the session tier; an explicit choice is the user's to make.

Notes, state them when relevant rather than dumping them every run:

  • New agent files hot-register mid-session, and live-value edits apply to the next spawn without a restart. The one exception: same-named overrides of built-ins (Explore, Plan) apply from the next session start.
  • CLAUDE_CODE_SUBAGENT_MODEL is never part of this switch; it is the emergency cost ceiling only, since it flattens every subagent to one model.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 23 lines · 21 tokens per session scan B 02134665c2e8

Subscribe to this mod's changes

model-routing is a command published in the GitHub repository JayOfemi/claude-harness-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 759 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.