Install
$ agentstack add skill-aiappsgbb-awesome-gbb-hosted-agent-deploy-expert ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
hostedagentdeploy_expert
When to use
- A user reports a failed
azd up,azd ai agent deploy, orazd deployfor a Foundry hosted agent - A scheduled task flags failed deployments in the monitored Foundry project
- A hosted agent starts but the first
/invokereturns errors
Investigation flow
- Identify the failed deploy — agent name, approximate time, which command the user ran.
- Check the Foundry project's deployments:
``bash az ml online-deployment list \ --workspace-name --resource-group \ --output table ` Capture instanceName, provisioningState, failureReason` for each failed deployment.
- Pull container logs from App Insights for the failure window:
``kql traces | where timestamp > ago(1h) | where cloud_RoleName == "" | where severityLevel >= 2 | project timestamp, message, severityLevel, customDimensions | top 50 by timestamp desc ``
- Classify by pattern:
| Pattern in logs | Root cause | KI | |---|---|---| | Authentication failed with provider ... (HTTP 401) | Foundry User missing at account scope | foundry-hosted-agents KI-001 | | cannot import name 'AzureOpenAIChatClient' from 'agent_framework.azure' | MAF SDK 1.4.0 breaking change | foundry-hosted-agents KI-002 (replace with OpenAIChatClient from agent_framework.openai) | | SkillsProvider object has no attribute 'skill_paths' | MAF API change | foundry-hosted-agents KI-003 (use SkillsProvider.from_paths(...)) | | Quota exceeded / OperationLimitExceeded | AOAI TPM cap hit | Hand off to quota_throttle_expert | | ImagePullBackOff / pull access denied | ACR pull failed | Grant AcrPull on the project's ACR to agent's UAMI | | 403 Forbidden /openai/deployments/... | Foundry MI lacks Cognitive Services User on BYOK AOAI | Grant role | | Request body must be a JSON object with a non-empty input string | azd ai agent invoke envelope bug | ghcp-hosted-agents KI-001 (use curl with {"input":"..."}) | | agent.yaml: services: block missing | azd ai agent init doesn't generate it | ghcp-hosted-agents KI-002 (add manually) |
- For 401 patterns, hand off to
byok_401_debug_expert. - For 429/quota, hand off to
quota_throttle_expert.
Tools
RunAzCliReadCommandsQueryAppInsightsByAppIdQueryLogAnalyticsByWorkspaceId
Safety
- Never display Foundry connection strings, AOAI keys, or ACR passwords
- Read-only investigation — every change suggestion is for the human to approve
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: aiappsgbb
- Source: aiappsgbb/awesome-gbb
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.