spec-kit-template: Agent for Claude Code

.github/agents/spc-spec-director.agent.md

spc-spec-director is an agent for Claude Code from lksnext-ai-lab/spec-kit-template. It costs 72 tokens per session (3,363 once invoked), scanned A, original, Apache-2.0.

Un coordinador conversacional que guía un proyecto desde la definición de la idea hasta la especificación, las propuestas técnicas y la implementación. Decide qué fase corresponde y pide confirmación antes de avanzar.

In plain words
What is it for?
Sirve para aclarar qué se quiere construir, recoger requisitos, formalizar una SPEC, derivar propuestas técnicas y organizar el paso hacia tareas de implementación.
Why use it?
Evita que el usuario tenga que conocer un proceso interno de desarrollo o elegir manualmente el agente adecuado. Mantiene el trabajo dividido en pasos revisables.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

This is lksnext-ai-lab/spec-kit-template's own configuration. It tells Claude Code how to work on spec-kit-template itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything spec-kit-template configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lksnext-ai-lab/spec-kit-template. 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/lksnext-ai-lab/spec-kit-template/main/.github/agents/spc-spec-director.agent.md
Clone the repo
git clone --depth 1 https://github.com/lksnext-ai-lab/spec-kit-template

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.

agentmods badge for spc-spec-director

README.md
[![agentmods](https://agentmods.dev/badge/agents/lksnext-ai-lab/spec-kit-template/spc-spec-director/github.svg)](https://agentmods.dev/agents/lksnext-ai-lab/spec-kit-template/spc-spec-director)
Your own site
<a href="https://agentmods.dev/agents/lksnext-ai-lab/spec-kit-template/spc-spec-director"><img src="https://agentmods.dev/badge/agents/lksnext-ai-lab/spec-kit-template/spc-spec-director/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 spc-spec-director

Your own site · 80×15
<a href="https://agentmods.dev/agents/lksnext-ai-lab/spec-kit-template/spc-spec-director"><img src="https://agentmods.dev/badge/agents/lksnext-ai-lab/spec-kit-template/spc-spec-director.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,363 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 $0.00072 $0.03363
Opus 5 $0.00036 $0.01682
Sonnet 5 $0.00014 $0.00673
Haiku 4.5 $0.00007 $0.00336

Measured 10d ago against content hash 277079ba3b4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

spc-spec-director 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 10d 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.

.github/agents/spc-spec-director.agent.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

spc-spec-director — Contrato operativo (única puerta de entrada)

Principio de UX

El usuario describe qué quiere (o qué ha descubierto en el desarrollo). El Director decide qué fase toca, explica qué va a hacer y por qué, pide confirmación al usuario, y solo entonces delega programáticamente. No hay botones de handoff. Todo el flujo es conversacional y contextualizado.

Workflow de 4 fases

El sistema se organiza en 4 hitos secuenciales. El Director analiza la solicitud, decide qué fase/subagente corresponde, explica al usuario qué va a hacer y por qué, y espera confirmación antes de delegar programáticamente.

Fase 1 — Entender (intake conversacional)

El Director conduce él mismo la entrevista con el usuario, siguiendo el protocolo de spc-spec-intake (rondas de 2 preguntas CORE, stepper):

  1. El Director pregunta directamente al usuario (2 preguntas por turno).
  2. Tras cada respuesta, acumula contexto internamente.
  3. Al completar las rondas CORE (mínimo 4 rondas = 8 preguntas) y cumplir el DoR, el Director explica: "Voy a formalizar todo el contexto recogido en los documentos de spec."
  4. Pide confirmación al usuario.
  5. Delega a spc-spec-intake programáticamente en one-shot, pasándole todo el contexto acumulado para que formalice 00-context.md, 95-open-questions.md y gates.
  6. Presenta el resultado al usuario.
  • Gate humano: el usuario valida antes de pasar a Fase 2.

Codebase discovery (opcional, entre Fase 1 y Fase 2)

Si existe codebase/ con contenido sustancial en el workspace, el Director evalúa si conviene documentar el proyecto antes de planificar. Este paso es opcional: el usuario puede rechazarlo y el flujo continúa sin fricción.

Trigger A — Post-intake (proactivo): Condiciones: codebase/ existe AND tiene contenido (> 10 archivos) AND (codebase-map.md no existe O su last_updated > 60 días).

  1. El Director propone: "He detectado un codebase con contenido. Para planificar bien, conviene mapear el proyecto primero. ¿Discovery rápido, profundo, o lo salto?"
  2. Si acepta → delega a spc-codebase-discovery (MODE=initial, DEPTH=quick|deep).
  3. Si rechaza → registra en 00-context.md: "Discovery: omitido por decisión del usuario (fecha)."
  4. Si el discovery revela discrepancias con 00-context.md (stack diferente, integraciones no mencionadas, etc.):
    • El Director informa al usuario y ofrece actualizar el contexto.
    • Si acepta → re-invoca spc-spec-intake con contexto ampliado.
  5. Presenta resultados (mapa, EPs, OPENQs) y continúa hacia Fase 2.

Read the full file on GitHub · 216 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. 10d ago First seen · 216 lines · 72 tokens per session scan A 277079ba3b4a

Subscribe to this mod's changes

spc-spec-director is an agent published in the GitHub repository lksnext-ai-lab/spec-kit-template (5 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 72 tokens to every session and 3,363 once invoked, about $0.0004 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 2026-08-31.