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 gabrielmoreira/agent-skills-mirror --skill swiftlys2-toolkitgit clone --depth 1 https://github.com/gabrielmoreira/agent-skills-mirrorWrote 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/gabrielmoreira/agent-skills-mirror/swiftlys2-toolkit)<a href="https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/swiftlys2-toolkit"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/swiftlys2-toolkit/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/gabrielmoreira/agent-skills-mirror/swiftlys2-toolkit"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/swiftlys2-toolkit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.02620 |
| Opus 5 | $0.00037 | $0.01310 |
| Sonnet 5 | $0.00015 | $0.00524 |
| Haiku 4.5 | $0.00007 | $0.00262 |
Grade A, and why
SwiftlyS2-Toolkit 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- swiftlys2-toolkit — 100% identical, 140 lines differ
How it starts
The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SwiftlyS2-Toolkit
This is a general-purpose toolkit entry for SwiftlyS2 C# / .NET plugin development.
Its goal is not to bind itself to any specific workspace, but to provide a publicly reusable workflow, rule set, template collection, and reference navigation system.
Public reference allowlist
The public docs, prompts, agents, and templates in this toolkit should, by default, reference only the following public sources:
- SwiftlyS2 official documentation:
https://swiftlys2.net/docs/ - sw2-mdwiki:
https://github.com/himenekocn/sw2-mdwiki - SwiftlyS2 official repository:
https://github.com/swiftly-solution/swiftlys2
If the current workspace has workspace-specific mappings, local reference repositories, historical reference projects, or special rules, that information may only be recorded in:
-
./copilot-instructions.md -
./knowledge-base.md -
If the workspace includes a local
sw2-mdwikicheckout, it is strongly recommended to use it as a local reference repository to improve agent retrieval efficiency and accuracy.
What this skill should produce
When using this skill, the preferred output should be one of the following:
- An implementation plan for a new plugin or new module
- A direct modification plan for an existing plugin
- A gap analysis for historical behavior alignment
- An audit of lifecycle, thread safety, high-frequency hooks, Schema, or Protobuf usage
- A method-level implementation plan
When to use it
Use this skill when the task involves:
- SwiftlyS2 plugin development
Commands,Events,Hooks,Modules,Workers,Services- High-frequency runtime loops and state synchronization
Schema,NetMessages,Protobuf, orIPlayerlifecycle handling- High-frequency hooks, async workers, main-thread-sensitive APIs, or entity lifecycle handling
- Plugin migration, behavior alignment, structural audits, or method-level planning
When not to use it
- Regular C# work unrelated to SwiftlyS2
- Pure frontend UI work
- A one-off tiny change that does not require architecture, lifecycle, or thread-boundary judgment
What ships with it
39 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.
- assets/development/commands/client-command-hook-template.cs.md 4.0 KB
- assets/development/commands/command-attribute-template.cs.md 3.2 KB
- assets/development/commands/command-service-template.cs.md 2.2 KB
- assets/development/configuration/config-hot-reload-template.cs.md 3.4 KB
- assets/development/configuration/README.md 958 B
- assets/development/convars/convar-template.cs.md 4.0 KB
- assets/development/core-events/lifecycle-checklist.md 2.0 KB
- assets/development/core-events/precache-resource-template.cs.md 2.8 KB
- assets/development/entity/schema-write-checklist.md 1.6 KB
- assets/development/game-events/game-events-usage-notes.md 2.8 KB
- assets/development/getting-started/partial-plugin-template.cs.md 1.8 KB
- assets/development/menus/menu-template.cs.md 7.3 KB
- assets/development/native-functions-and-hooks/hook-handler-template.cs.md 4.0 KB
- assets/development/netmessages/protobuf-handler-template.cs.md 1.7 KB
- assets/development/permissions/README.md 442 B
- assets/development/profiler/hotpath-gc-checklist.md 2.0 KB
- assets/development/scheduler/scheduler-vs-worker-guide.md 1.2 KB
- assets/development/shared-api/shared-interface-template.cs.md 4.6 KB
- assets/development/swiftly-core/core-service-entrypoints.md 1.5 KB
- assets/development/thread-safety/thread-sensitivity-checklist.md 2.3 KB
- assets/development/translations/README.md 373 B
- assets/development/using-attributes/attribute-registration-checklist.md 1.6 KB
- assets/guides/dependency-injection/di-service-plugin-template.cs.md 2.8 KB
- assets/guides/dependency-injection/service-template.cs.md 3.3 KB
- assets/guides/html-styling/README.md 9.6 KB
- assets/guides/terminologies/README.md 670 B
- assets/patterns/async-patterns/async-safety-guide.md 6.3 KB
- assets/patterns/background-workers/worker-template.cs.md 3.6 KB
- assets/patterns/per-player-state/player-state-management-guide.md 6.2 KB
- assets/patterns/service-factory/service-factory-template.cs.md 4.4 KB
- assets/README.md 6.6 KB
- assets/workflows/audit/audit-report-template.md 754 B
- assets/workflows/planning/method-level-plan-template.md 864 B
- README.en.md 4.8 KB
- README.md 4.1 KB
- references/swiftlys2-asset-inventory.md 4.5 KB
- references/swiftlys2-kb-index.md 12 KB
- references/swiftlys2-official-docs-map.md 21 KB
- references/swiftlys2-plugin-playbook.md 16 KB
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 · 299 lines · 75 tokens per session scan A 8f45ed00b46f
SwiftlyS2-Toolkit is a skill published in the GitHub repository gabrielmoreira/agent-skills-mirror (17 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 2,620 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
reflection-method-call
Call a C# method by reflection — including private methods. Requires a method schema obtained via 'reflection-method-find'. Supports static methods, instance methods (with optional target deserialization), and main-thread / off-thread execution.
script-execute
Compiles and executes C# code dynamically using Roslyn. Supports a full-code mode (default) and a body-only mode — see the skill body for the difference and for how to pass Unity object references as parameters.
reflection-method-find
Find C# methods across every loaded assembly by name / type / parameters — including private methods. Returns serialized MethodData entries usable as schemas for 'reflection-method-call'.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
script-delete
Delete one or more .cs script files from disk, refresh the AssetDatabase, and wait for Unity compilation to settle before delivering the final result via the request's requestId. Pair with 'script-read' to inspect files before deletion.
script-read
Read a .cs script file and return its content as a string. Supports a 1-based lineFrom/lineTo slice for partial reads. Pair with 'script-update-or-create' to write back.