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 franciscpd/batuta-compozy --skill batuta-routinggit clone --depth 1 https://github.com/franciscpd/batuta-compozyWrote 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/franciscpd/batuta-compozy/batuta-routing)<a href="https://agentmods.dev/skills/franciscpd/batuta-compozy/batuta-routing"><img src="https://agentmods.dev/badge/skills/franciscpd/batuta-compozy/batuta-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/franciscpd/batuta-compozy/batuta-routing"><img src="https://agentmods.dev/badge/skills/franciscpd/batuta-compozy/batuta-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 | $0.00050 | $0.01088 |
| Opus 5 | $0.00025 | $0.00544 |
| Sonnet 5 | $0.00010 | $0.00218 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade A, and why
batuta-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.
This is a copy
100% identical to batuta-routing — 24 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Batuta Routing Table
Batuta's core opinion: route every task to the cheapest executor that can
handle it. Lanes use the complexity vocabulary that cy-create-tasks
writes into task frontmatter (low, medium, high, critical) — the
same vocabulary runtime_rules[].match.complexity matches on.
Lane semantics (the durable opinion)
| Lane | Intent | Selection rule |
|---|---|---|
low |
Contained change, well-trodden paths | Cheapest coding-capable model in the catalog |
medium |
New interfaces, moderate coordination | Mid-tier coding model; raise reasoning before raising cost |
high |
New subsystem, heavy reasoning | Strong coding model, premium tier acceptable |
critical |
Cross-cutting, high regression risk | The operator's most trusted frontier model |
How batuta derives the concrete table (never copy an example)
compozy__provider_models_list(with costs) is the ONLY source of concrete provider/model IDs — it reflects the CLIs actually installed and the models actually discovered on this machine. A provider absent from the catalog is not installed; never route to it.- Map each lane's selection rule onto the catalog using the cost fields
(
input_per_million/output_per_million) as evidence. - Model enablement is account-side and invisible to the daemon — present the derived table (with costs) to the operator for confirmation before storing; ask what their accounts enable when in doubt.
Example only — derived on one machine on 2026-08-11, DO NOT reuse
On that machine the derivation produced: low → codex/gpt-5.6-luna,
medium → codex/gpt-5.6-terra@high, high → codex/gpt-5.6-sol,
critical → claude/claude-opus-4-8. Your catalog will differ; derive, do
not copy.
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 · 83 lines · 50 tokens per session scan A 5c9b98973426
batuta-routing is a skill published in the GitHub repository franciscpd/batuta-compozy (5 stars, last pushed 10d ago), licensed MIT. It adds 50 tokens to every session and 1,088 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to batuta-routing, differing in 24 lines, and is treated as a copy.
Other skills, from other repositories
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
pr-review-triage
Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.
trigger-authoring-tasks
Covers writing backend Trigger.dev tasks with @trigger.dev/sdk: defining task() and schemaTask(), the run function and its ctx, retries, waits, queues and concurrency, idempotency keys, run metadata, logging, triggering other tasks (and the Result shape), scheduled/cron tasks, and the essentials of trigger.config.ts.…