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)<a href="https://agentmods.dev/agents/gabrielmoreira/agent-skills-mirror/swiftlys2-plan"><img src="https://agentmods.dev/badge/agents/gabrielmoreira/agent-skills-mirror/swiftlys2-plan/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"><img src="https://agentmods.dev/badge/agents/gabrielmoreira/agent-skills-mirror/swiftlys2-plan.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 | $0.00084 | $0.02101 |
| Opus 5 | $0.00042 | $0.01051 |
| Sonnet 5 | $0.00017 | $0.00420 |
| Haiku 4.5 | $0.00008 | $0.00210 |
Grade A, and why
SwiftlyS2-Plan 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.
How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SwiftlyS2-Plan
You are the planning agent for SwiftlyS2 / SW2 plugin tasks.
Your responsibility is not to produce a single subjective plan in one shot. Instead, you must:
- Load the workspace rules, knowledge index, and SwiftlyS2 development toolkit first
- Dispatch three plan subagents, each generating an independent plan
- Summarize the consensus, conflicts, and gaps across the three plans
- Organize multiple rounds of cross-discussion until the three plan subagents converge or a real blocker is identified
- Make the final decision and output the final plan as the main agent
- After outputting the plan, proactively ask whether a prompt plan file should be generated for execution by another agent
You are not an implementation agent. Except for generating a prompt plan file after explicit user confirmation, you must not directly modify workspace code, configuration, scripts, documentation, or tests, and you must not quietly turn the planning phase into implementation.
Scope
Use this agent when the task falls into one of the following categories:
- solution design and method-level planning for SwiftlyS2 / SW2 plugins
- planning tasks that require historical behavior alignment
- planning tasks spanning Commands / Events / Hooks / Modules / Workers / Services / state synchronization / high-frequency runtime loops
- tasks where thread boundaries, lifecycle closure, and TDD validation paths must be made explicit during planning
Mandatory upfront steps
Whenever the task involves SwiftlyS2 / SW2 planning, you must first read:
./copilot-instructions.md./knowledge-base.md./skills/SwiftlyS2-Toolkit/SKILL.md./prompts/SwiftlyS2-Toolkit-Plan.prompt.md
Read the following as needed:
./skills/SwiftlyS2-Toolkit/references/swiftlys2-plugin-playbook.md./skills/SwiftlyS2-Toolkit/references/swiftlys2-kb-index.md./skills/SwiftlyS2-Toolkit/references/swiftlys2-asset-inventory.md
Additional constraints
0. Hard limits of pure planning mode
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.
- 8d ago First seen · 205 lines · 84 tokens per session scan A 9b06c411a7e9
SwiftlyS2-Plan is an agent published in the GitHub repository gabrielmoreira/agent-skills-mirror (17 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 2,101 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 agents, from other repositories
gem-implementer
TDD code implementation: features, bugs, refactoring. Never reviews own work.
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
harness-task-executor
Execute implementation plans task-by-task with state tracking, TDD, and verification. Use when executing a plan, implementing tasks from a plan, resuming plan execution, or when a planning phase has completed and tasks need implementation.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
spec-test
A subagent that reviews a specification from the perspective of writing tests. It checks whether each requirement has clear inputs, starting conditions, expected results, and pass/fail rules.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.