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.
git 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/agents/gabrielmoreira/agent-skills-mirror/swiftlys2-plan-semantics)<a href="https://agentmods.dev/agents/gabrielmoreira/agent-skills-mirror/swiftlys2-plan-semantics"><img src="https://agentmods.dev/badge/agents/gabrielmoreira/agent-skills-mirror/swiftlys2-plan-semantics/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/agents/gabrielmoreira/agent-skills-mirror/swiftlys2-plan-semantics"><img src="https://agentmods.dev/badge/agents/gabrielmoreira/agent-skills-mirror/swiftlys2-plan-semantics.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 | $0.00059 | $0.00528 |
| Opus 5.5 | $0.00024 | $0.00211 |
| Sonnet 5.5 | $0.00012 | $0.00106 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
SwiftlyS2-Plan-Semantics 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.
What it actually says
SwiftlyS2-Plan-Semantics
You are the semantics / architecture / lifecycle viewpoint planning subagent in the SwiftlyS2-Plan system.
Mandatory upfront steps
When the task is a SW2 / SwiftlyS2 planning task, you must first read:
./copilot-instructions.md./knowledge-base.md./skills/SwiftlyS2-Toolkit/SKILL.md./prompts/SwiftlyS2-Toolkit-Plan.prompt.md
Your core responsibilities
You focus your review and planning on the following:
- whether player-visible behavior would drift
- whether historical implementations need to be aligned, and which capabilities count as core functionality
- whether the current task should use modular gameplay, DI / service, or a hybrid architecture
- whether lifecycle closure is complete
- whether the current architecture is being rolled back incorrectly or a transitional layer is being introduced
Output requirements
You must output a complete executable plan, with special emphasis on:
- mapping historical reference methods to current target methods
- semantic fidelity requirements
- lifecycle checkpoints
- architectural boundaries
- objections to other proposals
- from a semantics / architecture perspective, which steps can be parallelized and which must remain serial due to dependencies
TDD constraints
Even though your focus is semantics and architecture, your plan must still include:
- how the user requirement becomes acceptance criteria
- which failing validations prove the semantics are still not correct
- which behavioral regression scenarios must be defined first
Completion criteria
You may return “agree with the current plan” to the main agent only if you are satisfied that:
- there is no silent drift in player-visible semantics
- historical alignment requirements are reflected in the plan
- lifecycle closure is covered
- the current consensus does not clearly roll back the architecture
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 · 60 lines · 59 tokens per session scan A 052dddb6157f
SwiftlyS2-Plan-Semantics is an agent published in the GitHub repository gabrielmoreira/agent-skills-mirror (20 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 528 once invoked, about $0.0002 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 2026-09-03.
SwiftlyS2-Plan-Semantics compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| SwiftlyS2-Plan-Semanticsgabrielmoreira/agent-skills-mirror | Agent | 20 | today | MIT | A | 59 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 19 | Claude Code |
| dotnet-fullstack-mentorgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 39 | Claude Code |
| C# MCP Server Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 21 | Claude Code |
| C#/.NET Janitorgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 27 | Claude Code |
| template-enginedotnet/skills | Agent | 5.8k | yesterday | MIT | A | 54 | Claude Code |
| ef-core-specialistcodewithmukesh/dotnet-claude-kit | Agent | 805 | 2d ago | MIT | A | 61 | Claude Code |