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 jakenuts/agent-skills --skill wolverinegit clone --depth 1 https://github.com/jakenuts/agent-skillsWrote 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/jakenuts/agent-skills/wolverine)<a href="https://agentmods.dev/skills/jakenuts/agent-skills/wolverine"><img src="https://agentmods.dev/badge/skills/jakenuts/agent-skills/wolverine/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/jakenuts/agent-skills/wolverine"><img src="https://agentmods.dev/badge/skills/jakenuts/agent-skills/wolverine.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 | $0.00172 | $0.02490 |
| Opus 5.5 | $0.00069 | $0.00996 |
| Sonnet 5.5 | $0.00034 | $0.00498 |
| Haiku 4.5 | $0.00017 | $0.00249 |
Grade A, and why
wolverine 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 2mo 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wolverine
WolverineFx is a .NET runtime for command execution and message handling. One mental model covers many use cases: a method handles a message; the rest is just where the message comes from and what happens after it succeeds.
- In-process mediator — invoke a command, run a handler. Lower ceremony than MediatR.
- Local message bus — fire-and-forget across in-memory queues with optional durability.
- Distributed messaging — same handler model, fronted by RabbitMQ, Azure Service Bus, SQS/SNS, Kafka, NATS, Pulsar, MQTT, Redis, GCP Pub/Sub, PostgreSQL, SQL Server, etc.
- HTTP endpoints —
WolverineFx.Httpexposes methods as ASP.NET Core endpoints with the same conventions. - Durable messaging — inbox/outbox on top of Marten, EF Core, or RavenDb for transactional consistency.
- Sagas / process managers — long-running stateful workflows.
CQRS and event sourcing are one thing Wolverine pairs well with (via Marten), but most features apply equally to plain command/event-driven services, modular monoliths, vertical-slice web apps, background workers, and ETL pipelines. Do not assume a Wolverine question implies event sourcing.
When agent context is tight
If you only need the API shape for a specific topic, read the matching reference file below and skip the rest. The list below is the index — load only what you need for the current task.
| Reference | Load when... |
|---|---|
| references/handlers.md | Writing or modifying a handler: discovery rules, signatures, cascading messages, side effects, return types, error policies, FluentValidation, [Entity] loading. |
| references/messaging.md | Sending/publishing/scheduling messages, routing rules, listener config, local queues, conventional routing, topics. |
| references/transports.md | Configuring a specific broker (RabbitMQ, Azure Service Bus, SQS, Kafka, NATS, Pulsar, MQTT, Redis, PostgreSQL/SQL Server transport). |
| references/http.md | Building or migrating WolverineFx.Http endpoints, mediator-style routes, response/request conventions. |
| references/durability.md | Enabling inbox/outbox, idempotency, dead letter storage, claim checks, transactional middleware. |
| references/persistence.md | Picking/wiring Marten, EF Core, or RavenDb integration; sagas; multi-tenancy; event sourcing aggregate handlers (only when actually using event sourcing). |
| references/middleware-and-policies.md | Writing conventional middleware, policies, attributes; modifying handler chains. |
| references/testing-and-ops.md | Tracked-session integration tests, command-line diagnostics, codegen, logging, health checks, AOT/cold-start tuning. |
| references/patterns.md | Architectural shape: vertical-slice, modular monolith, mediator-only, railway, ping-pong, leader election, MediatR/MVC/MinAPI migration. |
What ships with it
9 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.
- 2mo ago First seen · 145 lines · 172 tokens per session scan A 9797d2c7c168
wolverine is a skill published in the GitHub repository jakenuts/agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 172 tokens to every session and 2,490 once invoked, about $0.0007 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 2026-08-31.
wolverine compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wolverinejakenuts/agent-skills | Skill | 2 | 3mo ago | MIT | A | 172 | Claude Code, Codex |
| agui-dotnet-streaming-chatag-ui-protocol/ag-ui | Skill | 17k | yesterday | MIT | A | 223 | Claude Code |
| azure-maps-search-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 91 | Claude Code |
| azure-mgmt-apicenter-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 97 | Claude Code |
| create-datadriven-aspnetcoredotnet/skills | Skill | 5.8k | today | MIT | A | 147 | Claude Code |
| azure-ai-voicelive-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 92 | Claude Code |
| omnistudio-callable-apex-generateforcedotcom/sf-skills | Skill | 1.2k | yesterday | Apache-2.0 | A | 176 | Claude Code, Codex |