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.
npx skills add a275618631/codex-antigravity-collaboration --skill model-worker-routinggit clone --depth 1 https://github.com/a275618631/codex-antigravity-collaborationWrote 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/a275618631/codex-antigravity-collaboration/model-worker-routing)<a href="https://agentmods.dev/skills/a275618631/codex-antigravity-collaboration/model-worker-routing"><img src="https://agentmods.dev/badge/skills/a275618631/codex-antigravity-collaboration/model-worker-routing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/a275618631/codex-antigravity-collaboration/model-worker-routing"><img src="https://agentmods.dev/badge/skills/a275618631/codex-antigravity-collaboration/model-worker-routing.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00032 | $0.00826 |
| Opus 5 | $0.00016 | $0.00413 |
| Sonnet 5 | $0.00006 | $0.00165 |
| Haiku 4.5 | $0.00003 | $0.00083 |
Grade A, and why
model-worker-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 10d 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.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Worker Routing
Use this skill only for an explicit opt-in route. Do not infer delegation from task size, cost, token usage, or coding difficulty.
Trigger
Trigger only when the current user request explicitly contains Ox Alpha, including these forms:
本任務用 Ox Alpha本任務交給 Ox Alpha這個任務用 Ox Alpha這次用 Ox Alpha請用 Ox Alpha 執行本任務用 Ox Alpha 做這個任務本任務用 Ox Alpha 代替 SolUse Ox Alpha for this taskRun this task with Ox AlphaDelegate this task to Ox Alpha
Do not trigger for generic requests such as「修改這個 Repo」「跑 tests」「省 token」or「用便宜模型」.
Workflow
-
Preserve the user's task text, but send only the task and constraints to the worker. Do not send the full conversation, parent reasoning, or a pre-scanned repository dump.
-
Determine the current workspace from the active thread/cwd using
pwdand, when applicable,git rev-parse --show-toplevel. If the workspace cannot be determined reliably, stop with a concise workspace-needed message; do not guess. -
Validate that the workspace exists and is not a credential, system, home-root, or Codex-settings directory. A read-only task may inspect the current workspace; a write or write-test task must use an isolated/disposable workspace when the current workspace is dirty. Never overwrite uncommitted changes.
-
Choose the lowest deterministic permission mode:
readfor analyse, inspect, scan, review, explain, or risk-finding requests.writefor modify, fix, update, refactor, or add-file requests without a test requirement.write-testwhen the request also asks to run, verify, or pass tests. If uncertain, choose the lower mode.
-
Invoke the existing single source of truth exactly once:
python3 "${CODEX_HOME:-$HOME/.codex}/model-routing-mvp/route_task.py" \ --message "<original task containing the explicit Ox Alpha route>" \ --workspace "<validated workspace>" \ --workspace-root "<safe parent root>" \ --permission-mode "<read|write|write-test>"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 59 lines · 32 tokens per session scan A e8c81c65a092
model-worker-routing is a skill published in the GitHub repository a275618631/codex-antigravity-collaboration (8 stars, last pushed 10d ago), licensed MIT. It adds 32 tokens to every session and 826 once invoked, about $0.0002 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
architecture-decision-records
Comprehensive patterns for creating, maintaining, and managing Architecture Decision Records (ADRs) that capture the context and rationale behind significant technical decisions.
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
aria
Designs the data model, API contracts, and structural foundation of the system.
aws-sst-development
SST v4 (Ion) expert for managing AWS resources as code with the Pulumi-backed framework.
autonomous-agent-patterns
Design patterns for building autonomous coding agents, inspired by Cline and OpenAI Codex.
peon-ping-log
Log exercise reps for the Peon Trainer. Use when user says they did pushups, squats, or wants to log reps. Examples - "/peon-ping-log 25 pushups", "/peon-ping-log 30 squats", "log 50 pushups".