byok_401_debug_expert

byok_401_debug_expert is a skill for Claude Code, Codex from aiappsgbb/awesome-gbb. It costs 52 tokens per session (758 once invoked), scanned B, original, MIT.

A troubleshooting guide for a specific 401 authentication error when a Foundry-hosted agent uses a customer-owned Azure OpenAI account. BYOK means bringing your own service account or key.

In plain words
What is it for?
Use it to inspect the agent identity and Azure role assignments, then apply the documented account-level permission fix.
Why use it?
It checks whether the agent identity has the required Foundry User permission both on the project and on the underlying Cognitive Services account.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to inspect the agent identity and Azure role assignments, then apply the documented account-level permission fix.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aiappsgbb/awesome-gbb/byok_401_debug_expert
Install

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.

Any agent
npx skills add aiappsgbb/awesome-gbb --skill byok_401_debug_expert
Clone the repo
git clone --depth 1 https://github.com/aiappsgbb/awesome-gbb

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for byok_401_debug_expert

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiappsgbb/awesome-gbb/byok_401_debug_expert/github.svg)](https://agentmods.dev/skills/aiappsgbb/awesome-gbb/byok_401_debug_expert)
Your own site
<a href="https://agentmods.dev/skills/aiappsgbb/awesome-gbb/byok_401_debug_expert"><img src="https://agentmods.dev/badge/skills/aiappsgbb/awesome-gbb/byok_401_debug_expert/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.

agentmods 80×15 button for byok_401_debug_expert

Your own site · 80×15
<a href="https://agentmods.dev/skills/aiappsgbb/awesome-gbb/byok_401_debug_expert"><img src="https://agentmods.dev/badge/skills/aiappsgbb/awesome-gbb/byok_401_debug_expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 758 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.00758
Opus 5 $0.00026 $0.00379
Sonnet 5 $0.00010 $0.00152
Haiku 4.5 $0.00005 $0.00076

Measured 9d ago against content hash 1e089bb1f844, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

byok_401_debug_expert scanned grade B with 2 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 9d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -X POST <endpoint>/api/v1/invoke -H "Content-Type: application/json" -d '{"input":"hello"}'

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST <endpoint>/api/v1/invoke -H "Content-Type: application/json" -d '{"input":"hello"}'
skills/azure-sre-agent/references/plugins/gbb-foundry/skills/byok_401_debug_expert/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

byok_401_debug_expert

Background

When a Foundry hosted agent uses BYOK (bring-your-own-key) against a customer-owned Azure OpenAI account, the agent's identity needs Foundry User (RoleDefinitionId 53ca6127-db72-4b80-b1b0-d745d6d5456d) assigned at TWO scopes:

  • Project scopeazd ai agent deploy assigns this automatically
  • CognitiveServices account scope — NOT assigned automatically

Without the account-scope role, the agent starts and accepts /invoke calls (returns 200 with SSE stream), but the FIRST event in the stream is an error with the 401. This is the silent BYOK 401.

Investigation flow

  1. Get the agent's identity:

    az cognitiveservices account show --name <foundry-account> --resource-group <rg> --query "identity" -o json
    az ml online-endpoint show --workspace-name <project> --resource-group <rg> --name <endpoint> --query "identity" -o json
    
  2. List role assignments on the BYOK CognitiveServices account:

    az role assignment list \
      --scope /subscriptions/<sub>/resourceGroups/<rg>/providers/Microsoft.CognitiveServices/accounts/<account> \
      --role "Foundry User" -o table
    
  3. Match against the agent's identity. If the agent's UAMI principalId (or its instance_identity.principal_id) is NOT in the role assignment list at the ACCOUNT scope — that's the root cause.

  4. Verify the symptom in App Insights:

    traces
    | where timestamp > ago(2h)
    | where cloud_RoleName == "<agent-name>"
    | where message contains "Authentication failed with provider"
    | project timestamp, message, customDimensions
    
  5. Output the exact fix for the human to run:

    az role assignment create \
      --assignee <agent-uami-principalId> \
      --role "Foundry User" \
      --scope /subscriptions/<sub>/resourceGroups/<rg>/providers/Microsoft.CognitiveServices/accounts/<byok-account>
    

    Also grant to blueprint.principal_id if azd ai agent show reveals a separate blueprint identity.

Read the full file on GitHub · 80 lines

Changes

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.

  1. 9d ago First seen · 80 lines · 52 tokens per session scan B 1e089bb1f844

Subscribe to this mod's changes

byok_401_debug_expert is a skill published in the GitHub repository aiappsgbb/awesome-gbb (5 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 758 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens