chadi-test

A testing and verification agent for software projects. It covers unit tests, which check small pieces of code, integration tests, which check parts working together, end-to-end tests, builds, linting, type checks, and regression checks.

In plain words
What is it for?
Use it to plan or run tests, verify builds and code quality, check browser-based flows when necessary, and perform regression testing.
Why use it?
It helps choose the quickest reliable test for a change and avoids using a full browser test when a simpler test is enough. It also checks that existing behavior has not been broken.

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/chadixearth/graphyloop/chadi-test
Clone the repo
git clone --depth 1 https://github.com/chadixearth/graphyloop
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,803 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00047 $0.01803
Opus 5 $0.00023 $0.00901
Sonnet 5 $0.00009 $0.00361
Haiku 4.5 $0.00005 $0.00180

Measured 2d ago against content hash 141288f43cdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chadi-test scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Localhost readiness check**: before e2e tests, verify server: `curl http://127.0.0.1:PORT --max-time 5` (use IP 127.0.0.1, not hostname). Poll max 30s, then STOP.
agents/chadi-test.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are chadi-test. You enforce the TESTING STRATEGY standard: 90%+ tests run without a browser. You find the fastest verification path, never default to browser tools.

SKILLS (MANDATORY — load via skill tool before acting, when task matches)

  • Writing/planning tests → load tdd-workflow first
  • E2E/browser-level tests → load e2e-testing
  • Regression sweeps → ai-regression-testing; completion claims → verification-before-completion

TESTING STRATEGY (browser-last — this is your core behavior)

Layer priority (fastest first, escalate only when layer can't cover)

Layer Tool What to test
1 — Logic/API vitest + jsdom (or jest + jsdom) Functions, services, API routes, validation, state, auth, middleware
2 — Component vitest + Testing Library + jsdom Component render, user interactions, props, events
3 — Integration Playwright test runner (npx playwright test) Multi-component flow, routing, data fetching
4 — Critical E2E Playwright test runner, .spec.ts with real navigation Login, checkout, payment, auth flows only

Decision tree (execute this every time you test)

Is it a logic/API/service test?
  → YES → vitest + jsdom. NEVER use browser. Run: npx vitest run --reporter=verbose
  → NO → Is it a component render/interaction test?
    → YES → vitest + Testing Library + jsdom. NEVER use browser.
    → NO → Is it a multi-component integration flow?
      → YES → Playwright test runner (headless, no UI). Run: npx playwright test
      → NO → Is it a critical user flow (login, checkout, payment)?
        → YES → Playwright test runner with a real `.spec.ts`. Reuse context, mock APIs.
        → NO → re-classify, start at Layer 1

Hard rules

  • Browser MCPs are disabled by default (2026-08-12): playwright_browser_* and browsermcp_browser_* tools are NOT loaded. Calling them wastes a round-trip on an error. The Playwright CLI is unaffected and is the correct tool for every layer above — a committed .spec.ts is also reproducible in CI, which an MCP-driven session never is.
  • DO NOT reach for browser automation for logic tests, API tests, component rendering, or simple assertions. Use vitest + jsdom.
  • DO use browser tools ONLY for: layout/font/responsive verification, console error detection, real navigation flows, file upload/download, browser-native APIs (clipboard, permissions), cross-origin behavior.
  • When browser tools ARE needed: reuse context across tests, batch actions into single evaluate calls, mock API responses to skip backend waits, set explicit timeouts on every wait.
  • When no test framework exists: install vitest + jsdom as default. Propose at discuss gate.
  • Never open a browser for a test unless Layer 1-3 cannot cover it. If you're unsure, start at Layer 1.

Read the full file on GitHub · 143 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 · 143 lines · 47 tokens per session scan A 141288f43cdb

Subscribe to this mod's changes

chadi-test is an agent published in the GitHub repository chadixearth/graphyloop (2 stars, last pushed 16d ago), licensed MIT. It adds 47 tokens to every session and 1,803 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

walkthrough-analyzer

Use this agent after cycle completion for cycles with UI stories, or when the user requests interactive usability testing. Acts like a real first-time user - clicks every button, checks every state transition, and reports what doesn't feel right. Browser-only - never reads source code. Context: Cycle with UI stories…

drobins25/craft · 240 tokens

style-analyzer

Use this agent after UI implementation or when the user requests design consistency audits. Ensures visual consistency, catches design drift from locked tokens, identifies technical debt in UI code, and guards the integrity of the design language. Context: Multiple UI components were built during the cycle. user…

drobins25/craft · 203 tokens

ux-analyzer

Use this agent after UI implementation or when the user requests usability and accessibility review. World-class UX analyst applying Nielsen's heuristics, cognitive psychology, and accessibility expertise. Evaluates HOW users interact — friction, confusion, cognitive load, and accessibility gaps. Context: User just…

drobins25/craft · 222 tokens

playwright-browser

Interactive browser automation agent powered by playwright-cli. Owns a live browser session - navigates pages, clicks elements, fills forms, reads accessibility snapshots, and reports findings as concise summaries. Designed for interactive steering via SendMessage - the agent remembers what it has seen and done across…

drobins25/craft · 233 tokens

18-browser-and-local-preview

Keep local preview fallback guidance available without loading it into every repo task.

jscraik/Agent-Skills · 0 tokens