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.
npx agentmods add instructions/idavidov13/agentic-playwright/refactor-valuesgit clone --depth 1 https://github.com/idavidov13/agentic-playwrightWhat 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 | $0.01789 | $0.01789 |
| Opus 5 | $0.00894 | $0.00894 |
| Sonnet 5 | $0.00358 | $0.00358 |
| Haiku 4.5 | $0.00179 | $0.00179 |
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.
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:
- The enum key (the import reference consumers use).
- 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).
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.
- 2d ago First seen · 155 lines · 1,789 tokens per session scan A 81f71fb5d72c
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.
Other instructions, from other repositories
nuwax AGENTS.md
Instructions for nuwax-ai/nuwax, covering ai agent system documentation, 系统概述, ai agent 架构, 核心组件 and ai 功能特性.
qaskills AGENTS.md
Instructions for PramodDutta/qaskills, covering agents.md, project overview, common commands, run a single package and run tests in watch mode.
inspecto CLAUDE.md
Instructions for inspecto-dev/inspecto, covering inspecto — claude code development guide, project overview, monorepo structure, development phases (load each file as needed) and key architectural decisions.
qaskills CLAUDE.md
Instructions for PramodDutta/qaskills, covering claude.md, what this is, conventions (non-negotiable), commands and single package.
agentic-config AGENTS.md
Instructions for WaterplanAI/agentic-config, covering project guidelines, environment & tooling, core rules, skill triggering and content & pii.
compare-mcp CLAUDE.md
Instructions for Cristophereasygoing927/compare-mcp, covering compare-mcp, architecture, running and key decisions.