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 agentmods add skills/cveralyon/axel-setup/model-routingnpx skills add cveralyon/axel-setup --skill model-routinggit clone --depth 1 https://github.com/cveralyon/axel-setupWrote 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/cveralyon/axel-setup/model-routing)<a href="https://agentmods.dev/skills/cveralyon/axel-setup/model-routing"><img src="https://agentmods.dev/badge/skills/cveralyon/axel-setup/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 | $0.00080 | $0.01091 |
| Opus 5 | $0.00040 | $0.00545 |
| Sonnet 5 | $0.00016 | $0.00218 |
| Haiku 4.5 | $0.00008 | $0.00109 |
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 6d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Routing for Multi-Agent Orchestration
The main thread (Fable) is the orchestrator, architect, synthesizer, and final judge. Cheaper subagents do bounded, token-heavy work. Never delegate judgment.
Reserved for Fable (main thread, never spawn for this)
- Decomposing ambiguous work into clean parallel slices.
- Architecture, product, security, and payment-flow tradeoffs.
- Reading conflicting subagent reports and deciding what matters.
- Integrating partial implementations into one coherent plan.
- Final review, risk assessment, and user-facing synthesis.
Routing Table
Set the model param explicitly on every Agent call. Default to sonnet when a task does not match a row.
| Task type | model | Why |
|---|---|---|
| Broad codebase exploration, file/pattern discovery (Explore agents) | sonnet | High read volume, moderate judgment |
| Mechanical reduction: log filtering, test output triage, inventories, classification, link checking | haiku | Zero judgment, maximum volume |
| External docs research, dependency or vendor comparison | sonnet | Needs criteria but not deep tradeoffs |
| Bounded implementation from a precise, file-scoped spec (1 logical unit) | sonnet | Spec quality carries the work |
| Complex implementation, risky refactor, DB migrations, security or payment code | opus | Error cost exceeds the price delta |
| Code review, adversarial verification (excelsior-verifier, refute passes, skeptic agents) | opus | Must independently catch errors from other agents |
| Sub-coordinators that themselves spawn agents (cross-repo, debug session managers) | opus | Orchestration judgment without Fable price |
| Synthesis of conflicting findings, final verdicts, anything ambiguous | fable (stay in main thread) | This is the judgment layer |
Cost anchors per 1M tokens (input/output): haiku $1/$5, sonnet $3/$15, opus $5/$25, fable $10/$50. Fable's tokenizer also emits roughly 30% more tokens for the same content, so its effective cost is about 2.6x opus. Every token kept out of the main thread is saved at the most expensive rate in the catalog.
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.
- 6d ago First seen · 71 lines · 80 tokens per session scan A 33e0f18ffc58
model-routing is a skill published in the GitHub repository cveralyon/axel-setup (4 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 1,091 once invoked, about $0.0004 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
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约，产出 UI-DESIGN.md。四端通用。.
taiyi-evolve
TaiyiForge 辅助 — 实现后架构与文档同步（architecture-sync）。OpenCode / Claude / Codex / Cursor 通用。.
taiyi-diagram-c4
TaiyiForge 辅助 — 从代码反推 C4 架构文档（Observed/Inferred 分层 · Mermaid 真源）。OpenCode / Claude / Codex / Cursor 通用。.
retrospective-audit
Stage B of /prflow:retrospective-weekly: given a most-recent-first subset of one recurring pattern's occurrence-PR context bundles (bounded by auditbundlecap), re-derive the root cause and return one JSON object carrying a ranked findings array (one to three sub-patterns) — no edits, no worktree. Invoked as a subagent…
docs
Use when documentation generally needs to catch up with a branch before pushing or merging, covering internal developer docs, external customer-facing docs, and release notes together — "update the docs", "do a docs pass before I merge", "make sure everything's documented". Prefer this when no single documentation…
tmux-lane-orchestrator
Manage one tmux agent lane from its matching ops pane, inspect live pane state and Codex logs on cold start, and produce concise manager summaries for OpenClaw and adjacent project work.