An autonomous workflow for completing a software goal from its description. It uses Spec-Driven Development, a method that plans the requirements and work before checking the result.

Use it to build a feature or fix a problem from a desired outcome, then repeatedly implement and verify the work until it is finished or genuinely blocked.

It removes the need to give step-by-step prompts and helps keep implementation, checks, and project documents aligned. It also groups blocking questions at the start.

How kevinrivm/vocero-crm configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kevinrivm/vocero-crm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/kevinrivm/vocero-crm/main/.claude/skills/loop-sdd/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/kevinrivm/vocero-crm

Made for: Claude Code.

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/kevinrivm/vocero-crm/loop-sdd/github.svg)](https://agentmods.dev/skills/kevinrivm/vocero-crm/loop-sdd)

Your own site

<a href="https://agentmods.dev/skills/kevinrivm/vocero-crm/loop-sdd"><img src="https://agentmods.dev/badge/skills/kevinrivm/vocero-crm/loop-sdd/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/kevinrivm/vocero-crm/loop-sdd"><img src="https://agentmods.dev/badge/skills/kevinrivm/vocero-crm/loop-sdd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,121 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00140	$0.01121
Opus 5	$0.00070	$0.00561
Sonnet 5	$0.00028	$0.00224
Haiku 4.5	$0.00014	$0.00112

Measured 13d ago against content hash eed7f6b096f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

loop-sdd 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 13d 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.

.claude/skills/loop-sdd/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Loop SDD — ejecutar objetivos, no prompts

El dueño da objetivos; tú corres el loop completo y vuelves solo al terminar o al bloquearte de verdad. Es la implementación de Goal→Work→Check→Repeat (no Ask→Answer→Stop) sobre el flujo Spec Kit de este repo. El contrato canónico vive en CLAUDE.md → "Modo Objetivo — Loop SDD" y "Definición de Hecho REFORZADA"; este skill es el punto de entrada.

Entrada

El argumento es el objetivo (qué debe lograrse / cómo debe comportarse el producto). Si no se pasó argumento, toma el último objetivo que el dueño describió en la conversación.

El loop (no saltes Verify)

Discover — Lee el estado real antes de actuar: spec/plan/tasks de la feature activa, código relevante, memoria (MEMORY.md + archivos), y logs si hay un bug. Decide si el objetivo necesita una spec nueva (speckit-specify + speckit-clarify) o si es una corrección/extensión sobre una feature existente.
- Agrupa TODAS las preguntas bloqueantes y hazlas UNA sola vez aquí. Si puedes resolver algo con defaults sensatos o leyendo el código, hazlo; no preguntes.
Plan — speckit-plan → speckit-tasks → speckit-analyze. Para correcciones pequeñas, un plan ligero basta, pero deja el alcance explícito.
Execute — speckit-implement (o la edición directa para fixes acotados). Respeta el stack y la constitución del proyecto (tipos estrictos, multi-tenant si aplica, idempotencia, secretos cifrados).
Verify (OBLIGATORIO — lo hace el agente, no el dueño) —
- Gate técnico: typecheck + lint + build (los comandos reales del proyecto).
- Self-test de comportamiento E2E: despliega (o corre local) y ejerce el flujo real como usuario, con la herramienta adecuada (navegador, API, línea de prueba del canal). Conduce el flujo completo de punta a punta, no una llamada aislada.
- Camino infeliz: provoca lo que el sistema/proveedor exponen (input inválido, respuesta vacía/no-formato, fuera de ventana, fallo del proveedor) y comprueba que degrada sin colgarse.
- Confirma el resultado observable con evidencia (transcripción/captura/log), no solo un 2xx del endpoint ni "compila".

Read the full file on GitHub · 74 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.

13d ago First seen · 74 lines · 140 tokens per session scan A eed7f6b096f3

Subscribe to this mod's changes

loop-sdd is a skill published in the GitHub repository kevinrivm/vocero-crm (168 stars, last pushed 6d ago), licensed MIT. It adds 140 tokens to every session and 1,121 once invoked, about $0.0007 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.

Building agents Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

vocero-crm: Skill for Claude Code