test-selection

test-selection is a skill for Claude Code, Codex from joinwell52-AI/CodeFlowMu-open. It costs 35 tokens per session (275 once invoked), scanned A, original, MIT.

A guide for choosing how much verification to run after a code change, from focused tests to broader package, type, or browser checks.

In plain words
What is it for?
Select appropriate unit, package, typecheck, UI, and browser verification based on the change's scope, then document what was run and omitted.
Why use it?
It prevents both under-testing risky changes and spending time on unrelated test suites. It also requires reporting skipped checks and remaining risk.

Skill for Claude CodeCodex

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 skills/joinwell52-ai/codeflowmu-open/test-selection
Any agent
npx skills add joinwell52-AI/CodeFlowMu-open --skill test-selection
Clone the repo
git clone --depth 1 https://github.com/joinwell52-AI/CodeFlowMu-open

Made for: Claude Code, Codex.

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 test-selection

README.md
[![agentmods](https://agentmods.dev/badge/skills/joinwell52-ai/codeflowmu-open/test-selection.svg)](https://agentmods.dev/skills/joinwell52-ai/codeflowmu-open/test-selection)
Your own site
<a href="https://agentmods.dev/skills/joinwell52-ai/codeflowmu-open/test-selection"><img src="https://agentmods.dev/badge/skills/joinwell52-ai/codeflowmu-open/test-selection.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 275 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 $0.00035 $0.00275
Opus 5 $0.00017 $0.00138
Sonnet 5 $0.00007 $0.00055
Haiku 4.5 $0.00003 $0.00028

Measured 3d ago against content hash 9a991057ac04, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-selection 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 3d 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.

skills/test-selection/SKILL.md · 44 lines

What it actually says

Test Selection

When to use

Use after planning or making a change to decide which checks should run and which risks remain if some checks are skipped.

Rules

  • Match test scope to blast radius.
  • For single-module logic, run the closest unit tests first.
  • For shared runtime/router/API behavior, add or run package-level tests.
  • For UI/browser-visible behavior, include Playwright or browser verification when feasible.
  • Run typecheck when changing exported types or TypeScript contracts.
  • Name skipped checks and why they were skipped.

Required output

When reporting, include:

  • Checks run.
  • Checks skipped.
  • Why the selected scope is sufficient.
  • Residual risk.

Forbidden actions

  • Do not say "tested" without naming the check.
  • Do not rely only on snapshots or static reading for interactive UI behavior.
  • Do not run unrelated expensive suites just to look thorough when a narrower suite proves the change.

Minimal example

Focused: SkillContextRouter.test.ts
Broader: AgentPlaybookCatalog.test.ts because manifest shape changed
Skipped: full shell typecheck due known pre-existing errors
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. 3d ago First seen · 44 lines · 35 tokens per session scan A 9a991057ac04

Subscribe to this mod's changes

test-selection is a skill published in the GitHub repository joinwell52-AI/CodeFlowMu-open (2 stars, last pushed 9d ago), licensed MIT. It adds 35 tokens to every session and 275 once invoked, about $0.0002 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.