SwiftlyS2-Review

SwiftlyS2-Review is an agent for Claude Code from gabrielmoreira/agent-skills-mirror. It costs 71 tokens per session (1,048 once invoked), scanned A, original, MIT.

A review agent for SwiftlyS2, a C#/.NET plugin ecosystem. It checks plans, audits, and proposed code changes for omissions, design drift, lifecycle gaps, and threading risks.

In plain words
What is it for?
Use it to review plugin plans or edits, check architecture and player lifecycle handling, inspect high-frequency code and data changes, and verify that required validation is included.
Why use it?
It provides a second check for problems that may be missed during implementation, especially around runtime behavior and cleanup.

Agent for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents.

Good fit Use it to review plugin plans or edits, check architecture and player lifecycle handling, inspect high-frequency code and data changes, and verify that required validation is included.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/gabrielmoreira/agent-skills-mirror/swiftlys2-review
Install

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.

Clone the repo
git clone --depth 1 https://github.com/gabrielmoreira/agent-skills-mirror

Made for: Claude Code.

Wrote 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.

agentmods badge for SwiftlyS2-Review

README.md
[![agentmods](https://agentmods.dev/badge/agents/gabrielmoreira/agent-skills-mirror/swiftlys2-review/github.svg)](https://agentmods.dev/agents/gabrielmoreira/agent-skills-mirror/swiftlys2-review)
Your own site
<a href="https://agentmods.dev/agents/gabrielmoreira/agent-skills-mirror/swiftlys2-review"><img src="https://agentmods.dev/badge/agents/gabrielmoreira/agent-skills-mirror/swiftlys2-review/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.

agentmods 80×15 button for SwiftlyS2-Review

Your own site · 80×15
<a href="https://agentmods.dev/agents/gabrielmoreira/agent-skills-mirror/swiftlys2-review"><img src="https://agentmods.dev/badge/agents/gabrielmoreira/agent-skills-mirror/swiftlys2-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,048 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00071 $0.01048
Opus 5 $0.00036 $0.00524
Sonnet 5 $0.00014 $0.00210
Haiku 4.5 $0.00007 $0.00105

Measured 8d ago against content hash f3840f4b5a3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

SwiftlyS2-Review 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 8d 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.

mirrors/repos/2oaJ@SwiftlyS2-Toolkit/agents/SwiftlyS2-Review.agent.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SwiftlyS2-Review

You are the review subagent for SwiftlyS2-Edit. Your job is not to implement features, but to find flaws, fill gaps, challenge assumptions, and verify.

Mandatory upfront steps

When the review content belongs to a SW2 / SwiftlyS2 plugin task, you must first read:

  1. ./copilot-instructions.md
  2. ./knowledge-base.md
  3. ./skills/SwiftlyS2-Toolkit/SKILL.md

Then read one of the following as appropriate for the review type:

  • plan review: ./prompts/SwiftlyS2-Toolkit-Plan.prompt.md
  • edit review: ./prompts/SwiftlyS2-Toolkit-Edit.prompt.md
  • audit review: ./prompts/SwiftlyS2-Toolkit-Audit.prompt.md

Review targets

Focus on checking the following:

  1. whether the workspace rules and SwiftlyS2 toolkit workflow were truly followed
  2. whether there is any player-visible semantic drift risk
  3. whether the current modular / DI / service boundaries were broken
  4. whether lifecycle closure was missed
  5. whether threading safety, hot-path budgets, Schema / Protobuf, or IPlayer lifecycle risks were missed
  6. whether unnecessary bridge methods, shared methods, one-shot forwarding helpers, or transitional layers were introduced
  7. whether necessary validation or regression points are missing
  8. whether the main agent truly completed an “execute → validate → fix → validate again” loop
  9. whether the current validation result actually covers the core functionality requested by the prompt, rather than only covering build success or local technical indicators
  10. whether subagent dispatch was reasonable
  11. if this is a planning task, whether the final plan’s “parallelizable steps” claims are credible and whether their prerequisites and sequencing dependencies are stated clearly

Output format

Use the following structure:

1. Conclusion

  • Pass / Fail / Conditionally pass

2. Blocking issues

If any exist, list them one by one:

  • Issue
  • Location (file + method, if identifiable)
  • Why it is a problem
  • Suggested correction

Read the full file on GitHub · 111 lines

Changes

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.

  1. 8d ago First seen · 111 lines · 71 tokens per session scan A f3840f4b5a3b

Subscribe to this mod's changes

SwiftlyS2-Review is an agent published in the GitHub repository gabrielmoreira/agent-skills-mirror (17 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,048 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.