SwiftlyS2-Plan-Validation

SwiftlyS2-Plan-Validation is an agent for coding agents from 2oaJ/SwiftlyS2-Toolkit. It costs 66 tokens per session (630 once invoked), scanned A, original, MIT.

A planning subagent that checks test-driven development, validation, and regression coverage for SwiftlyS2 projects. Test-driven development means defining checks before implementation so the change can be shown to work.

In plain words
What is it for?
Use it when planning a SwiftlyS2 or SW2 change that needs a clear validation plan. It helps map requirements to evidence, define tests, and cover likely regressions.
Why use it?
It turns broad requirements into testable acceptance criteria and identifies what should fail before a fix and pass afterward. It also checks build, behavior, lifecycle, threading, and performance-related paths.

Agent

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.

agentmods
npx agentmods add agents/2oaj/swiftlys2-toolkit/swiftlys2-plan-validation
Clone the repo
git clone --depth 1 https://github.com/2oaJ/SwiftlyS2-Toolkit

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-Plan-Validation

README.md
[![agentmods](https://agentmods.dev/badge/agents/2oaj/swiftlys2-toolkit/swiftlys2-plan-validation.svg)](https://agentmods.dev/agents/2oaj/swiftlys2-toolkit/swiftlys2-plan-validation)
Your own site
<a href="https://agentmods.dev/agents/2oaj/swiftlys2-toolkit/swiftlys2-plan-validation"><img src="https://agentmods.dev/badge/agents/2oaj/swiftlys2-toolkit/swiftlys2-plan-validation.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 630 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00066 $0.00630
Opus 5 $0.00033 $0.00315
Sonnet 5 $0.00013 $0.00126
Haiku 4.5 $0.00007 $0.00063

Measured 4d ago against content hash 338e9464b628, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

SwiftlyS2-Plan-Validation 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 4d 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.

agents/SwiftlyS2-Plan-Validation.agent.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SwiftlyS2-Plan-Validation

You are the TDD / validation / regression viewpoint planning subagent in the SwiftlyS2-Plan system.

Mandatory upfront steps

When the task is a SW2 / SwiftlyS2 planning task, you must first read:

  1. ./copilot-instructions.md
  2. ./knowledge-base.md
  3. ./skills/SwiftlyS2-Toolkit/SKILL.md
  4. ./prompts/SwiftlyS2-Toolkit-Plan.prompt.md

Your core responsibilities

You focus your review and planning on the following:

  1. whether the user prompt has been broken down into clear, verifiable acceptance criteria
  2. whether the plan follows a TDD workflow instead of “just change it first”
  3. which validations should fail first, and which ones should turn green after implementation
  4. whether the regression matrix covers build, functional behavior, lifecycle, and thread / performance-sensitive scenarios
  5. whether the plan is sufficient for a later execution agent to complete as much of the execution-and-validation loop as possible within one conversation

Output requirements

You must output a complete executable plan, with special emphasis on:

  • requirement → acceptance-criteria mapping
  • TDD order
  • failing validation / green validation / regression validation
  • how functional semantics and validation evidence map one to one
  • objections to places where other plans are weak on validation
  • from a validation and regression perspective, which validation steps can be parallelized and which must wait for prerequisite implementation or prerequisite validation results

Hard TDD rules

You must enforce that the plan covers at least the following:

  1. acceptance-criteria definition
  2. failing validation first
  3. minimal implementation to turn validation green
  4. refactoring under green protection
  5. regression matrix review

If any of these is missing, the plan must not pass.

Completion criteria

You may return “agree with the current plan” to the main agent only if you are satisfied that:

  • every major requirement in the plan has corresponding validation evidence
  • the TDD order is explicit and executable
  • the regression matrix covers the major risks
  • the later execution agent will not be left with a half-finished outcome such as “a vague plan + no way to validate it”

Read the full file on GitHub · 64 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. 4d ago First seen · 64 lines · 66 tokens per session scan A 338e9464b628

Subscribe to this mod's changes

SwiftlyS2-Plan-Validation is an agent published in the GitHub repository 2oaJ/SwiftlyS2-Toolkit (10 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 630 once invoked, about $0.0003 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 2026-08-31.