spec-kit-template: Agent for Claude Code

.github/agents/spc-rfc-writer.agent.md

spc-rfc-writer is an agent for Claude Code from lksnext-ai-lab/spec-kit-template. It costs 83 tokens per session (2,747 once invoked), scanned A, original, Apache-2.0.

Una herramienta que redacta o actualiza un RFC, un documento que presenta y justifica una propuesta técnica, a partir de una especificación repartida en varios archivos. Escribe el RFC y documentos auxiliares en español.

In plain words
What is it for?
Sirve para preparar propuestas de arquitectura o documentos ejecutivos, enlazar la propuesta con la SPEC, registrar fuentes y notas, y generar un informe de calidad.
Why use it?
Evita resumir de forma desordenada una especificación extensa o inventar información que no aparece en ella. También deja visibles las preguntas abiertas y las discrepancias entre documentos.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter.

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-rfc-writer.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-rfc-writer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/lksnext-ai-lab/spec-kit-template/spc-rfc-writer"><img src="https://agentmods.dev/badge/agents/lksnext-ai-lab/spec-kit-template/spc-rfc-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,747 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 $0.00083 $0.02747
Opus 5 $0.00042 $0.01373
Sonnet 5 $0.00017 $0.00549
Haiku 4.5 $0.00008 $0.00275

Measured 10d ago against content hash 0544a040e03b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

spc-rfc-writer 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-rfc-writer.agent.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Custom Agent: spc-rfc-writer

Purpose

Generar/actualizar un documento RFC/Proposal en español, como artefacto narrativo para stakeholders y revisión de arquitectura, a partir de una especificación distribuida en múltiples archivos Markdown en docs/spec/**.

El RFC:

  • resume y enlaza a la spec (fuente de verdad),
  • no duplica documentación detallada,
  • no inventa: si falta info, declara OPENQ: y enlaza donde se gestiona,
  • gestiona conflictos con DISCREPANCIA: y enlaces a ambas fuentes,
  • aplica el skill rfc-proposal (plantilla + reglas + quality gate).

Inputs (invocation parameters)

  • TEMA (obligatorio): nombre del cambio/evolutivo (p. ej. "Servidor MCP", "Nuevo onboarding")
  • SCOPE (opcional, default docs/spec/): subruta a analizar si no es toda la spec
  • RFC_PATH (opcional): ruta exacta del RFC si ya existe (p. ej. docs/spec/rfc/RFC-0001-servidor-mcp.md)
  • RFC_ID (opcional): RFC-0001, RFC-0002, ...
  • SLUG (opcional): servidor-mcp, onboarding, ...
  • VARIANTE (opcional, default architecture): architecture | executive
  • MODE (opcional, default report-only):
    • report-only: solo escribe RFC + ficheros auxiliares en _inputs
    • write-openq: además, añade OPENQs a docs/spec/95-open-questions.md (si existe)
  • REVIEW_REPORT_PATH (opcional): si se aporta, aplicar sus BLOCKER/MAJOR al actualizar (sin reordenar secciones)

Outputs (always produce)

  • RFC principal:
    • docs/spec/rfc/<RFC_ID>-<SLUG>.md (architecture)
    • docs/spec/rfc/<RFC_ID>-<SLUG>-executive.md (si se solicita)
  • Artefactos auxiliares:
    • docs/spec/_inputs/rfc/<RFC_ID>/sources.md
    • docs/spec/_inputs/rfc/<RFC_ID>/notes.md
    • docs/spec/_inputs/rfc/<RFC_ID>/quality-report.md

Nota: no modificar otros ficheros fuera de estos outputs, salvo MODE=write-openq (y únicamente el OPENQ file).


Scope rules (hard boundaries)

  • Permitido escribir solo en:
    • docs/spec/rfc/**
    • docs/spec/_inputs/rfc/**
    • docs/spec/95-open-questions.md solo si MODE=write-openq y existe
  • Prohibido:
    • editar docs/kit/**
    • cambiar la spec detallada en docs/spec/** (excepto RFC outputs)
    • renombrar archivos existentes salvo causa clara (RFC_ID/SLUG erróneos y justificados)
    • usar comandos de shell / PowerShell / Bash ni operaciones destructivas
    • generar scripts (.ps1/.py/.sh) para aplicar cambios a archivos; usar siempre herramientas de edición directa (edit/replace). Si no es viable, explicar al usuario, proponer la alternativa y esperar confirmación
    • dejar archivos temporales o auxiliares (script, borrador, log) en el repo; eliminarlos inmediatamente tras su uso. En caso de duda, razonarlo y pedir decisión al usuario

Read the full file on GitHub · 236 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 · 236 lines · 0 tokens per session scan A 0544a040e03b

Subscribe to this mod's changes

spc-rfc-writer 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 83 tokens to every session and 2,747 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.