Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add vsladkov/claudex-stereo/plugin install stereoWrote 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.
[](https://agentmods.dev/skills/vsladkov/claudex-stereo/model-routing)<a href="https://agentmods.dev/skills/vsladkov/claudex-stereo/model-routing"><img src="https://agentmods.dev/badge/skills/vsladkov/claudex-stereo/model-routing.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.05521 |
| Opus 5 | $0.00012 | $0.02760 |
| Sonnet 5 | $0.00005 | $0.01104 |
| Haiku 4.5 | $0.00002 | $0.00552 |
Grade A, and why
model-routing scanned grade A with 0 findings 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 yesterday.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Routing
Apply these rules whenever a Stereo command routes a planner, reviewer, implementer, or adversarial reviewer. Let the command's step-specific prompts and loop rules override generic wording here.
Model addressing
Interpret selections as follows:
| Selection | Route |
|---|---|
claude:session |
Run inline in the current Claude session |
claude:inherit |
Run the named foreground agent with the model parameter omitted |
claude:sonnet |
Run the named foreground agent with model: "sonnet" |
claude:opus |
Run the named foreground agent with model: "opus" |
claude:haiku |
Run the named foreground agent with model: "haiku" |
claude:fable |
Run the named foreground agent with model: "fable" |
claude:opus-4.8 |
Run the role's -opus-4-8 agent twin (stereo:planner-opus-4-8, stereo:plan-reviewer-opus-4-8, stereo:implementer-opus-4-8, stereo:implementation-reviewer-opus-4-8, stereo:reviewer-opus-4-8, stereo:adversarial-reviewer-opus-4-8) with the model parameter omitted; those definitions pin claude-opus-4-8 |
codex:<selection> |
The written form for Codex-side models; pass it to the companion unchanged — it strips exactly one leading codex: prefix |
| Anything else | A bare Codex selection, equivalent to its codex: form; pass it to the companion unchanged |
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.
- yesterday Changed · +6 lines be1467144009
- 8d ago First seen · 402 lines · 23 tokens per session scan A 4243634b0569
model-routing is a skill published in the GitHub repository vsladkov/claudex-stereo (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 23 tokens to every session and 5,521 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
goal-test
A local experiment for testing a goal command that keeps an AI coding session working until a stated condition is judged complete. It uses a separate language model to evaluate the conversation after each assistant turn.
detect-task
Internal skill for commands. Detect the active task (any tracker adapter) from the task-state file / git branch name. Do not trigger on user conversation - only when commands need task detection.
loop-test
A local experiment for designing repeating checks with Claude Code’s loop command. It covers both fixed intervals and checks that schedule themselves again after each run.
take-task
A workflow for claiming a tracker task and preparing the development branch for it. It verifies the task, marks it as in progress, checks for uncommitted changes, and handles branch setup according to the task state.
goal-plan-clean
A guide for creating a reusable plan-review loop. It repeatedly checks a plan, fixes blocking issues and suggestions, and stops after approval or a small number of review rounds.
loop-bb-pr
A command that prepares a repeating check for a Bitbucket pull request. A pull request is a request to review and merge code changes into a project.