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 agents/cloudrift-ai/emmy/discover-modelsgit clone --depth 1 https://github.com/cloudrift-ai/emmyWrote 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/agents/cloudrift-ai/emmy/discover-models)<a href="https://agentmods.dev/agents/cloudrift-ai/emmy/discover-models"><img src="https://agentmods.dev/badge/agents/cloudrift-ai/emmy/discover-models.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 | $0.00011 | $0.00231 |
| Opus 5 | $0.00005 | $0.00115 |
| Sonnet 5 | $0.00002 | $0.00046 |
| Haiku 4.5 | $0.00001 | $0.00023 |
Grade A, and why
discover-models 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 4d 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.
What it actually says
You are Emmy's non-interactive model discovery agent. Load the discover-models skill before doing task work and
follow its attached lifecycle and scoring prompts exactly. Delegate the bounded source investigations and recipe
batches requested there, reconcile their evidence yourself, never modify the checkout, and return the requested
selection JSON object as the only final text.
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.
- 4d ago First seen · 34 lines · 11 tokens per session scan A 2cf03f0b664f
discover-models is an agent published in the GitHub repository cloudrift-ai/emmy (80 stars, last pushed 4d ago), licensed Apache-2.0. It adds 11 tokens to every session and 231 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
coding-agent-provider-taxonomy
This document summarizes how promptfoo should think about coding-agent providers, what has been implemented so far, and what should come next. It is intentionally implementation-facing: use it when planning provider work, reviewing feature gaps, or deciding where a new capability belongs.
overview
NVIDIA Dynamo adds agent-aware serving features without taking ownership of the agent loop: your harness still manages prompts, tools, subagents, and reasoning state, while Dynamo uses metadata attached to each LLM request to correlate work, improve routing and scheduling, manage KV cache behavior, and produce traces…
agent-hints
Agent hints are optional per-request metadata that a harness sends under nvext.agenthints. Dynamo parses these hints in the frontend and passes them to the router and, where supported, backend runtimes.
task-agents
The primary agent workflow — inference setup resolution, the automation switch, evidence-first execution, tool policy, and the proposal/confirmation loop.
matrix
This page renders the Tier-1 agent × model-family integration matrix truthfully from the authoritative test suite in tests/integrations/ — the matrix cells (testagentsmatrix.py), the family aliases and strict-xfail rules (conftest.py), and the pilot run recorded in tests/integrations/README.md.
opencode
Point OpenCode at a local rapid-mlx server. OpenCode is a Claude-Code-like terminal coding agent that speaks the OpenAI-compatible chat completions API (POST /v1/chat/completions) via the @ai-sdk/openai-compatible provider.