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 commands/azure/ai-gateway/discovergit clone --depth 1 https://github.com/Azure/ai-gatewayWrote 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/commands/azure/ai-gateway/discover)<a href="https://agentmods.dev/commands/azure/ai-gateway/discover"><img src="https://agentmods.dev/badge/commands/azure/ai-gateway/discover.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 | $0.00021 | $0.00522 |
| Opus 5 | $0.00010 | $0.00261 |
| Sonnet 5 | $0.00004 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
discover 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
/ai-gateway:discover
Discover — and only discover — the AI assets registered in an AI Gateway. This is a
read-only exploration command: it lists models and MCP tool servers and helps the
user pick the ones that match their intent. It never provisions, updates, or deletes
anything, and it does not scaffold code (use /ai-gateway:build for that).
Follow the discovery workflow defined in the bundled skill
skills/use-ai-gateway/SKILL.md — specifically Part 1 — Discover & select assets:
- Determine the target gateway from
$ARGUMENTSif provided. Discovery goes through the ARM control plane, so you need the gateway's ARMgatewayResourceId— a runtime host alone is not enough to list assets. If only a host is given, resolve the id (az resource list --name <name>) or ask the user. If the target is missing or ambiguous, ask before making any call. The gateway is aMicrosoft.ApiManagement/serviceorMicrosoft.ApiManagement/aigatewaysresource; both work identically. - List the models in the gateway workspace and read each model's
properties.deployment.modelName(the exact identifier accepted by the OpenAI passthrough — prefer it over the ARMnameordisplayName). - List the MCP tool servers, build each MCP endpoint URL as
https://{gateway-host}/default/toolservers/{toolServerName}/mcp(the/default/workspace segment is required), and verify each server actually exposes tools via a fullinitialize→notifications/initialized→tools/listMCP handshake (carry theMcp-Session-Idfrominitialize). Read the runtime host from the resource'sproperties.gatewayUrl. - Present a clear, grouped summary: models (id + description) and tool servers (name + endpoint + tool count), highlighting the best matches for the user's stated use case. Then ask which assets they want to use.
Stop after presenting the assets. Do not retrieve credentials or generate code unless
the user explicitly asks to continue (or runs /ai-gateway:build).
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 · 37 lines · 21 tokens per session scan A fd2234f1bcfd
discover is a command published in the GitHub repository Azure/ai-gateway (3 stars, last pushed 7d ago), licensed MIT. It adds 21 tokens to every session and 522 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.