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 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/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/cveralyon/axel-setup/model-routing"><img src="https://agentmods.dev/badge/skills/cveralyon/axel-setup/model-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 | $0.00080 | $0.01091 |
| Opus 5.5 | $0.00032 | $0.00436 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 3mo ago), licensed MIT. It adds 80 tokens to every session and 1,091 once invoked, about $0.0003 per session on Opus 5.5. 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
pr-triage
A pull-request review tool that checks a proposed set of code changes in a Git repository. A pull request is a request to merge one branch of code into another.
release-notes
A release-note generator that turns Git history and referenced issues into release notes following the Keep a Changelog format.
pave-catalog
Build a service catalog — schema, starter entries, and governance model. Produces what information to capture per service, how it's maintained, and where it lives. Use when asked to "service catalog", "what services do we have", "catalog our services", "service inventory", or "who owns what".
docs-audit
A scheduled review that looks for documentation that may no longer match recently changed source code. It examines Git history and searches documentation for references to changed files or names.
pave-golden
Define a golden path — the opinionated, supported way to do a common developer task (create a new service, set up an environment, deploy a feature). Produces concrete steps, templates, and tooling. Use when asked to "golden path", "create project template", "scaffold a new service", "how should we create services", or…
review-backlog-killer
Detect pull requests aging past warn / critical thresholds, score severity, and nudge reviewers via Slack DM, channel, email, or directly as a PR comment — with one-time auto-escalation when a PR hits critical so velocity stops leaking through review queues.