agentic-playwright refactor-values.instructions.md

A procedure for safely changing shared enum values, enum keys, or fixed test data in a TypeScript test project. An enum is a named list of allowed values.

In plain words
What is it for?
Use it before changing an enum member, renaming a key, or editing existing static data, followed by type checks, linting, and affected tests.
Why use it?
It requires finding all consumers first, so schemas, tests, page objects, and assertions do not silently drift apart.

Instructions file for GitHub Copilot

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 instructions/idavidov13/agentic-playwright/refactor-values
Clone the repo
git clone --depth 1 https://github.com/idavidov13/agentic-playwright

Made for: GitHub Copilot.

Per session 1,789 This file is loaded in full into every session.
When invoked 1,789 The same file — it is already loaded in full.
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 $0.01789 $0.01789
Opus 5 $0.00894 $0.00894
Sonnet 5 $0.00358 $0.00358
Haiku 4.5 $0.00179 $0.00179

Measured 2d ago against content hash 81f71fb5d72c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentic-playwright refactor-values.instructions.md 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 2d 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.

.github/instructions/refactor-values.instructions.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refactoring Enum Values and Static Test Data

Critical

  • ALWAYS run Phase 1 (find all consumers) before making any edit. Enum values and static data feed into tests, page objects, schemas, and assertions — the blast radius must be known up front.
  • ALWAYS search for both the enum key (Messages.LOGIN_ERROR) and the raw string value ('Invalid email or password'). Some consumers may have bypassed the enum and hardcoded the string — they won't update when you change the enum.
  • NEVER update an enum value, rename a key, or edit a static-data file without updating every consumer in the same commit (atomicity — no intermediate broken state).
  • NEVER loosen a Zod schema (z.literal / z.enum) to make an updated value pass. Update the schema to match the new value; the schema is the contract.
  • ALWAYS run npx tsc --noEmit + npx eslint . + the affected tests before concluding the refactor. TypeScript catches key renames; eslint catches stale patterns; tests catch assertion drift.
  • NEVER use a single global find-and-replace — it misses case variants, hardcoded copies, and references inside comments, documentation, and sibling skill files. Inspect each match.

Instructions

Phase 1: Find all consumers before touching anything

Search the entire codebase for every occurrence of both:

  1. The enum key (the import reference consumers use).
  2. The current string value (the raw string — catches hardcoded usages that bypass the enum).

Use rg (ripgrep) when available — faster and more ergonomic — or grep -r as a universal fallback:

# Find all usages of the enum key
rg "Messages.LOGIN_ERROR" .
grep -r "Messages.LOGIN_ERROR" .

# Find all usages of the raw string value
rg "Invalid email or password" .
grep -r "Invalid email or password" .

# For endpoint changes, search both
rg "ApiEndpoints.LOGIN" .
rg "'/api/users/login'" .

Do this before making any edits. Understand the full blast radius first. Expect matches in .ts, .tsx, .md (instruction files, README, CHANGELOG), and .json (Playwright reports — ignore).

Read the full file on GitHub · 155 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. 2d ago First seen · 155 lines · 1,789 tokens per session scan A 81f71fb5d72c

Subscribe to this mod's changes

agentic-playwright refactor-values.instructions.md is an instructions file published in the GitHub repository idavidov13/agentic-playwright (134 stars, last pushed 5d ago), licensed MIT. It adds 1,789 tokens to every session, about $0.0089 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 2026-08-30.