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 aiappsgbb/awesome-gbb --skill jwt_403_debug_expertgit clone --depth 1 https://github.com/aiappsgbb/awesome-gbbWrote 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/aiappsgbb/awesome-gbb/jwt_403_debug_expert)<a href="https://agentmods.dev/skills/aiappsgbb/awesome-gbb/jwt_403_debug_expert"><img src="https://agentmods.dev/badge/skills/aiappsgbb/awesome-gbb/jwt_403_debug_expert.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 5.1 | $0.00043 | $0.00626 |
| Opus 5 | $0.00022 | $0.00313 |
| Sonnet 5 | $0.00009 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
jwt_403_debug_expert 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 7d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
jwt_403_debug_expert
When to use
The SRE Agent should invoke this skill when:
- A user reports a 401 or 403 from the Citadel gateway
- A hosted agent's BYOK call returns "Authentication failed with provider … (HTTP 401)" but the underlying provider is the Citadel-routed AOAI
- After running
citadel-spoke-onboarding, the new spoke can't reach the gateway
Investigation flow
-
Get the correlation ID of the failing request from the user or from the application's logs.
-
Pull the request from APIM diagnostics:
ApiManagementGatewayLogs | where TimeGenerated > ago(2h) | where CorrelationId == "<id>" | project TimeGenerated, OperationId, ApiId, ProductId, ResponseCode, BackendStatusReason, LastErrorReason, RequestHeaders, ResponseHeaders -
Decode the JWT if present (claims only — NEVER the signature):
aud— must match the gateway URL configured in the Access Contractiss— must behttps://login.microsoftonline.com/<tenant>/v2.0oid— the calling principal's object IDscp/roles— must include the operation scope (e.g.llm:read)exp— must not be in the past
-
Match against the Access Contract:
Symptom Root cause Fix audmismatchToken issued for wrong audience Re-issue token with correct audience Missing scope claim Access Contract didn't grant this scope Re-run citadel-spoke-onboarding with the needed scope in gbb_access_contractsexpin pastToken expired (default ~1h for MI) Refresh; check caller's token-cache TTL No AuthorizationheaderCaller using product-key path but no key Set Ocp-Apim-Subscription-Keyor switch to JWT403 with valid JWT Per-product policy denies Check rate-limit-by-keyand product subscription state -
Output: classification, root cause hypothesis, ONE recommended fix and ONE verification step.
Tools
This skill uses:
RunAzCliReadCommandsQueryLogAnalyticsByWorkspaceId
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.
- 7d ago First seen · 60 lines · 43 tokens per session scan A 40491ef39983
jwt_403_debug_expert is a skill published in the GitHub repository aiappsgbb/awesome-gbb (5 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 626 once invoked, about $0.0002 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 skills, from other repositories
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
convex-performance-audit
Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.
convex-insights
Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.
ssl-proxy-troubleshoot
Systematic workflow for troubleshooting SSL/proxy connectivity issues with government websites.
diagnose-backend-bug
Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…
axiom-networking
Use when implementing or debugging ANY network connection, API call, or socket. Covers URLSession, Network.framework, NetworkConnection, connection diagnostics.