A workflow that plans, generates, and repairs end-to-end tests from approved acceptance criteria for web and mobile apps. It traces tests back to requirements and classifies failures as repairs, flaky tests, or real bugs.

Use it to create a test plan, prepare selectors, generate an executable suite, run it, and route failures to safe repair or bug-fixing work.

It provides one process from requirements to runnable tests instead of leaving planning, test creation, and failure triage disconnected. It also prevents test failures from being silently treated as harmless.

test-loop — Skill for Codex by HoangNguyen0403

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.

Any agent

npx skills add HoangNguyen0403/agent-skills-standard --skill test-loop

Clone the repo

git clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standard

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/test-loop/github.svg)](https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/test-loop)

Your own site

<a href="https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/test-loop"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/test-loop/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/test-loop"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/test-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 797 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00025	$0.00797
Opus 5	$0.00013	$0.00398
Sonnet 5	$0.00005	$0.00159
Haiku 4.5	$0.00003	$0.00080

Measured 5d ago against content hash e1be1f524f9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

test-loop 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 5d 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.

.codex/skills/test-loop/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Loop Skill

[!IMPORTANT] Plan, generate, and heal an executable E2E test suite from approved acceptance criteria (web and mobile).

Instructions

When the user asks to perform this workflow, execute the following steps:

Test Loop Workflow

Goal: Turn approved ACs into an executable, traced E2E suite, and classify any failure as a repair or a real bug instead of leaving it to manual triage.

Steps

Load scope:
- slug, operator_profile (carried, not re-inferred), AC-*, SRS lanes, build/app target, matched testing skills for the target stack.
Plan:
- Run specialist-test-planner to produce test_plan_path and selector_gaps (the specialist's PLAN: becomes this workflow's test_plan_path; SELECTOR_GAPS: becomes selector_gaps).
- BLOCKED (no stable AC-* trace) if no stable AC-* trace exists; route to plan-feature/design-solution.
Prepare selectors (Phase P1, not yet implemented):
- Run specialist-testid-inserter on selector_gaps; stop for approval when production files change in interactive mode.
Generate (Phase P1, not yet implemented):
- One scenario per specialist-integration-test-generator call, seed-first, using the MCP/tool matching the scenario's lane.
Run and heal (Phase P3, not yet implemented):
- Run once; per failure, run specialist-test-healer. HEALED requires 3 green reruns. REAL_BUG_DO_NOT_HEAL routes to dev-fix. QUARANTINE_CANDIDATE routes to quality-engineering-flaky-triage with a ticket.
Handoff:
- Route to verify-work with the generated suite and any unresolved real_bugs[].

Runtime Contract

Use after implement-feature reaches GREEN, or whenever ACs have E2E/mobile lanes without executable coverage.
Required inputs: slug, stable AC-* trace, a runnable build/app target.
Return BLOCKED (no build target or AC trace) only when the build target cannot be established or AC-* is missing.

Read the full file on GitHub · 69 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.

5d ago First seen · 69 lines · 25 tokens per session scan A e1be1f524f9f

Subscribe to this mod's changes

test-loop is a skill published in the GitHub repository HoangNguyen0403/agent-skills-standard (565 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 797 once invoked, about $0.0001 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 2026-09-07.

E2E testing Planning React Testing best-practices coding-standards flutter nestjs nextjs

verify

Build/launch/drive recipe for verifying apps/docs changes at runtime (demos, docs pages, llms.txt).

meursyphus/ssgoi · 26 tokens

testing-guide

A testing guide covering the test pyramid and standards for unit, integration, system, and end-to-end tests.

AsiaOstrich/universal-dev-standards · 152 tokens

next-partial-prefetching-optimizer

Optimize what selected Next.js client navigations include before the click under Partial Prefetching. Use after Cache Components and Partial Prefetching are adopted when the user wants selected URL-specific UI to be instant, wants reusable content to wait for navigation, or needs to choose between default, viewport…

vercel/next.js · 82 tokens

patrol-e2e-testing

Use when writing E2E/integration tests, testing native interactions like permissions or system dialogs, capturing UI regressions, or validating cross-platform behavior (Patrol 4.x).

evanca/flutter-ai-rules · 43 tokens

testing

Use when writing or reviewing Flutter/Dart tests (unit, widget, golden), fixing flaky tests, adding coverage, or choosing between unit and widget tests.

evanca/flutter-ai-rules · 33 tokens

flutter-mcp-cli-runtime-validation

Run Flutter MCP runtime validation from CLI in two steps (launch app, then run validate-runtime), including toolkit-extension gating, screenshot/layout capture, app error collection, optional reload verification, and retry handling for transient first-connect failures.

Arenukvern/mcp_flutter · 52 tokens