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 tallesborges/zdx --skill model-provider-mgmtgit clone --depth 1 https://github.com/tallesborges/zdxWrote 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/tallesborges/zdx/model-provider-mgmt)<a href="https://agentmods.dev/skills/tallesborges/zdx/model-provider-mgmt"><img src="https://agentmods.dev/badge/skills/tallesborges/zdx/model-provider-mgmt/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/tallesborges/zdx/model-provider-mgmt"><img src="https://agentmods.dev/badge/skills/tallesborges/zdx/model-provider-mgmt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00085 | $0.03426 |
| Opus 5.5 | $0.00034 | $0.01370 |
| Sonnet 5.5 | $0.00017 | $0.00685 |
| Haiku 4.5 | $0.00009 | $0.00343 |
Grade A, and why
model-provider-mgmt 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model & Provider Management
Covers three workflows: adding a model to an existing provider, adding a new provider from scratch, and regenerating/updating the default registry. All paths converge at just update-defaults which regenerates both default_config.toml and default_models.toml.
Quick reference
| Task | Rust file to edit | Then run |
|---|---|---|
| Add model (existing provider) | crates/zdx-engine/src/config.rs → default_<provider>_provider() |
just update-defaults |
| Update pricing/context only | crates/zdx-assets/default_models.toml (manual edit after generation) |
just ci-fast |
| Add new provider | Multiple (see below) | just update-defaults && just ci-fast |
Workflow 1: Add a model to an existing provider
1. Update the Rust model allow-list
Edit crates/zdx-engine/src/config.rs. Find fn default_<provider>_provider() and add the model ID to the models vec. Model IDs must match what the provider's API expects.
fn default_<provider>_provider() -> ProviderConfig {
ProviderConfig {
enabled: Some(true),
models: vec![
"<new-model-id>".to_string(), // ← added
"<existing-model-id>".to_string(),
// ...
],
..Default::default()
}
}
2. Regenerate defaults
just update-defaults
This runs update-config (regenerates crates/zdx-assets/default_config.toml from Rust defaults) then update-models (fetches pricing/capabilities from models.dev + OpenRouter fallback, writes crates/zdx-assets/default_models.toml).
3. Verify and fix the generated entry
Always inspect the generated entry. The updater pulls from models.dev and OpenRouter, which may have:
- Stale or promotional pricing (vs official provider docs)
- Wrong context limits (e.g. OpenRouter may report a pricing tier boundary instead of actual context window)
- Missing capabilities (e.g.
input_imagesdefaults to false)
Check crates/zdx-assets/default_models.toml for the new [[model]] block. Correct any fields that don't match the provider's official docs. Key fields:
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 Changed · +2 lines 8be28a01f840
- 1mo ago First seen · 231 lines · 85 tokens per session scan A 70b789c50987
model-provider-mgmt is a skill published in the GitHub repository tallesborges/zdx (20 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 3,426 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…