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 wardawgmalvicious/agent-config --skill azure-accessgit clone --depth 1 https://github.com/wardawgmalvicious/agent-configWrote 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/wardawgmalvicious/agent-config/azure-access)<a href="https://agentmods.dev/skills/wardawgmalvicious/agent-config/azure-access"><img src="https://agentmods.dev/badge/skills/wardawgmalvicious/agent-config/azure-access/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.
<a href="https://agentmods.dev/skills/wardawgmalvicious/agent-config/azure-access"><img src="https://agentmods.dev/badge/skills/wardawgmalvicious/agent-config/azure-access.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00206 | $0.05228 |
| Opus 5.5 | $0.00082 | $0.02091 |
| Sonnet 5.5 | $0.00041 | $0.01046 |
| Haiku 4.5 | $0.00021 | $0.00523 |
Grade A, and why
azure-access 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 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.
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 — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure access: give X access to Y, and find why X is refused
Most Azure access failures come down to four things: the wrong identity is calling, its role sits on the wrong plane, the role was never assigned because whoever deployed could not assign roles, or the change has not reached the caller yet. This skill walks them in that order, for an identity calling Key Vault, Storage or Container Registry from a deploy pipeline or a running app.
Dated, and drilled from Microsoft Learn and az 2.90.0 on
2026-10-17. No command here was run against a tenant; a line marked
unverified says what was not checked.
Not here. Fabric workspace roles and OneLake permissions, which
Azure RBAC does not govern. The Container Apps runtime: ingress,
probes, revisions. Bicep syntax and its green-build traps,
principalType among them, belong to the rule that loads with
*.bicep; GitHub's half of OIDC, the subject each trigger puts in the
token, to the rule that loads with .github/workflows/*.yml. Sign-in
policy for people: Conditional Access and MFA. Data roles for Cosmos
DB, Service Bus, SQL and other services were not drilled.
Detail lives in references/: roles.md (the data-plane roles per
service, Contributor's exclusions, who holds which write, both
permission models), errors.md (401 and 403 codes by service, deploy
errors, AADSTS codes in Learn's words) and credentials.md (credential
types, lifetimes, Key Vault's expiry semantics). Each cites the Learn
page behind its claims.
1. Pin the tenant, then name the caller
Pin the tenant before any az call, as ~/.claude/CLAUDE.md §
"Azure CLI state is per tenant, and pinned by folder" says: an unpinned
shell answers from whatever tenant the shared config last held, and
every listing below then describes the wrong directory.
Every identity has two IDs, and each command wants one. A managed
identity or service principal has a client (application) ID and a
principal (object) ID. Role assignments take the principal ID:
--assignee-object-id is "The assignee's object ID (also known as
principal ID)", and skips the Microsoft Graph lookup --assignee makes.
azure/login's client-id, AZURE_CLIENT_ID and the SDKs' client_id
take the client ID.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 403 lines · 206 tokens per session scan A 4423d47d7767
azure-access is a skill published in the GitHub repository wardawgmalvicious/agent-config (1 stars, last pushed 10d ago), licensed MIT. It adds 206 tokens to every session and 5,228 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-10-18.
Other skills, from other repositories
azure-mgmt-applicationinsights-dotnet
Azure Application Insights SDK for .NET. Application performance monitoring and observability resource management. Use for creating Application Insights components, web tests, workbooks, analytics items, and API keys. Triggers: "Application Insights", "ApplicationInsights", "App Insights", "APM", "application…
azure-resource-manager-mysql-dotnet
Azure MySQL Flexible Server SDK for .NET. Database management for MySQL Flexible Server deployments. Use for creating servers, databases, firewall rules, configurations, backups, and high availability. Triggers: "MySQL", "MySqlFlexibleServer", "MySQL Flexible Server", "Azure Database for MySQL", "MySQL database…
azure-eventhub-dotnet
Azure Event Hubs SDK for .NET. Use for high-throughput event streaming: sending events (EventHubProducerClient, EventHubBufferedProducerClient), receiving events (EventProcessorClient with checkpointing), partition management, and real-time data ingestion. Triggers: "Event Hubs", "event streaming"…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
azure-resource-manager-durabletask-dotnet
Azure Resource Manager SDK for Durable Task Scheduler in .NET. Use for MANAGEMENT PLANE operations: creating/managing Durable Task Schedulers, Task Hubs, and retention policies via Azure Resource Manager. Triggers: "Durable Task Scheduler", "create scheduler", "task hub", "DurableTaskSchedulerResource", "provision…
azure-resource-manager-sql-dotnet
Azure Resource Manager SDK for Azure SQL in .NET. Use for MANAGEMENT PLANE operations: creating/managing SQL servers, databases, elastic pools, firewall rules, and failover groups via Azure Resource Manager. NOT for data plane operations (executing queries) - use Microsoft.Data.SqlClient for that. Triggers: "SQL…