agentmods.dev

uat

uat is a command for Claude Code from 686f6c61/alfred-dev. It costs 19 tokens per session (616 once invoked), scanned A, original, MIT.

A command for preparing and recording human acceptance testing (UAT), the final check by a person that a deliverable works as expected.

In plain words
What is it for?
Use it to prepare a UAT checklist, mark the deliverable approved or rejected, or reopen the check for another review.
Why use it?
It keeps manual approval, rejection, notes, and next steps recorded separately from automated test results.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the AskUserQuestion tool; mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 .claude/alfred-continuity.py verify "$PWD" --raw "$ARGUMENTS".

Part of the alfred-dev plugin — 11 skills, 22 commands, 10 agents, 5 hooks, 1 MCP server shipped together

not rated 117repo 2mo ago A scan 19 tokens original MIT

Good fit Use it to prepare a UAT checklist, mark the deliverable approved or rejected, or reopen the check for another review.

Compare 6 commands from other repositories ↓
View source ↗ 686f6c61/alfred-dev alfred-dev.com
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/686f6c61/alfred-dev
agentmods
npx agentmods add commands/686f6c61/alfred-dev/uat

Made for: Claude Code.

Or install alfred-dev, the plugin that ships this one along with the rest of its 11 skills, 22 commands, 10 agents, 5 hooks, 1 MCP server.

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 uat

README.md
[![agentmods](https://agentmods.dev/badge/commands/686f6c61/alfred-dev/uat/github.svg)](https://agentmods.dev/commands/686f6c61/alfred-dev/uat)
Your own site
<a href="https://agentmods.dev/commands/686f6c61/alfred-dev/uat"><img src="https://agentmods.dev/badge/commands/686f6c61/alfred-dev/uat/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.

agentmods 80×15 button for uat

Your own site · 80×15
<a href="https://agentmods.dev/commands/686f6c61/alfred-dev/uat"><img src="https://agentmods.dev/badge/commands/686f6c61/alfred-dev/uat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 616 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.00616
Opus 5.5 $0.00008 $0.00246
Sonnet 5.5 $0.00004 $0.00123
Haiku 4.5 $0.00002 $0.00062

Measured 1mo ago against content hash f29aa7031db0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

uat 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 1mo 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.

commands/uat.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/alfred-dev:uat

Eres Alfred. Tu trabajo aquí es cerrar la validación humana del entregable, no reinterpretar los tests automáticos.

Argumento libre del usuario: $ARGUMENTS

Semántica del comando

  • Sin argumento: prepara o refresca la UAT actual y deja el checklist listo.
  • aprobado ...: registra que la validación manual ha quedado aprobada.
  • rechazado ...: registra que la validación manual ha fallado y guarda la nota.
  • pendiente ...: reabre o reinicia la UAT para volver a pasarla.

Protocolo

  1. Como .claude/* es sensible en Claude Code, NO uses Write ni Edit para los artefactos de UAT. Usa Bash y el helper del plugin inmediatamente:
python3 .claude/alfred-continuity.py verify "$PWD" --raw "$ARGUMENTS"

  1. Ese helper debe crear o actualizar estos artefactos:

    • .claude/alfred-uat.json
    • docs/project/uat.md

  2. Si el helper devuelve una respuesta válida, úsala como respuesta final y termina. El helper ya deja visibles el estado, el objetivo, el checklist, las notas y el siguiente paso.

  3. Solo si el helper falla, cae al modo manual y entonces lee este contexto en este orden:

    • .claude/alfred-dev-state.json
    • .claude/alfred-handoff.json
    • .claude/alfred-uat.json si existe
    • docs/project/current.md si existe
    • docs/project/codebase-map.md si existe
    • docs/project/uat.md si existe

  4. Si existe una sesión activa y fase_actual NO es completado, NO inventes una aceptación manual prematura. Indica que primero hay que cerrar o retomar ese flujo con /alfred-dev:resume o /alfred-dev:next.

Restricciones

  • NO uses AskUserQuestion como paso obligatorio dentro de /alfred-dev:verify.
  • NO marques una UAT como aprobada sin una indicación explícita del usuario.
  • NO borres el estado del flujo completado que originó la validación.
  • NO añadas una segunda capa de resumen si el helper ya dejó Estado, Objetivo, Checklist, Notas y Siguiente paso.
  • Si la UAT queda pendiente, termina indicando cómo registrar el resultado: /alfred-dev:verify aprobado o /alfred-dev:verify rechazado <nota>.

Read the full file on GitHub · 59 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. 1mo ago First seen · 59 lines · 19 tokens per session scan A f29aa7031db0

Subscribe to this mod's changes

uat is a command published in the GitHub repository 686f6c61/alfred-dev (117 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 616 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude CodeTestingai-agentsautomationclaude-code-pluginsdlc
Related

Other commands, from other repositories

e2e-test

Generate end-to-end tests using Playwright (web) and Detox (mobile). Covers user flows, visual regression, and cross-browser testing. Usage: /e2e-test [flow-name|--all] [--visual].

alphaaiservice/cortex · 46 tokens

gen-tests

Auto-generate comprehensive tests for a file or module. Usage: /gen-tests or /gen-tests --all-untested.

alphaaiservice/cortex · 29 tokens

perf-test

Generate and run performance/load tests using k6 or Locust. Benchmark API endpoints, detect bottlenecks, generate reports. Usage: /perf-test [endpoint-or-all] [--users=100] [--duration=60s].

alphaaiservice/cortex · 48 tokens

kill-mutants

Analyze surviving mutants from a mutation testing run and write targeted unit tests to kill them. Re-runs mutations to confirm kills.

swingerman/engineer · 29 tokens

record

Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.

MarcosNahuel/antigravity-plugin-cc · 38 tokens

mutate

Run mutation testing to verify test quality. Builds a custom mutation tool or uses an existing framework, runs mutations, and reports the mutation score with surviving mutants.

swingerman/engineer · 34 tokens