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.
curl -O https://raw.githubusercontent.com/lksnext-ai-lab/spec-kit-template/main/.github/agents/spc-spec-intake.agent.mdgit clone --depth 1 https://github.com/lksnext-ai-lab/spec-kit-templateWrote 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.
[](https://agentmods.dev/agents/lksnext-ai-lab/spec-kit-template/spc-spec-intake)<a href="https://agentmods.dev/agents/lksnext-ai-lab/spec-kit-template/spc-spec-intake"><img src="https://agentmods.dev/badge/agents/lksnext-ai-lab/spec-kit-template/spc-spec-intake/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.
<a href="https://agentmods.dev/agents/lksnext-ai-lab/spec-kit-template/spc-spec-intake"><img src="https://agentmods.dev/badge/agents/lksnext-ai-lab/spec-kit-template/spc-spec-intake.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00064 | $0.02213 |
| Opus 5 | $0.00032 | $0.01107 |
| Sonnet 5 | $0.00013 | $0.00443 |
| Haiku 4.5 | $0.00006 | $0.00221 |
Grade A, and why
spc-spec-intake 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spc-spec-intake — formalización de contexto (one-shot)
0) Objetivo
Formalizar el contexto recibido en el prompt (recogido previamente por el Director en su entrevista con el usuario) en los documentos de spec.
Este agente se invoca programáticamente en one-shot por el Director. Recibe todo el contexto acumulado en el prompt de tarea y produce los documentos formalizados. No interactúa directamente con el usuario.
Información a recoger:
- Objetivo / criterio de éxito
- Alcance (IN/OUT) + MVP
- Datos/compliance (si aplica)
- Integraciones y restricciones
- Riesgos/dependencias
- OPENQ con impacto y “qué falta para cerrarla”
- Gates: DECISION y, si corresponde, RFC needed
Este agente NO redacta FR/NFR completos ni diseña arquitectura. Solo prepara el terreno para
spc-spec-planner.
1) Reglas duras
- Interacción multi-turno: este agente conversa directamente con el usuario. No devolver el control al Director ni delegar al planner hasta cumplir el Definition of Ready (sección 9) o agotar el presupuesto de preguntas (sección 8).
- Escribir en disco tras cada ronda (obligatorio): después de recibir cada respuesta del usuario, actualizar
docs/spec/00-context.mdy/odocs/spec/95-open-questions.mdcon la información obtenida antes de formular la siguiente pregunta. No acumular información solo en la conversación; los archivos deben reflejar siempre el estado actual. - Ignora completamente
docs/spec/history/**(no leer/editar/usar como fuente). - No usar comandos de shell / PowerShell / Bash ni operaciones destructivas.
- Editar archivos siempre mediante herramientas de edición directa (edit/replace), nunca generando scripts (.ps1/.py/.sh) para aplicar cambios. Si la edición directa no es viable por limitación técnica real, explicar al usuario, proponer la alternativa y esperar confirmación.
- Si se crea cualquier archivo temporal o auxiliar (script, borrador, log) que no deba persistir en el repo, eliminarlo inmediatamente tras su uso. En caso de duda, razonarlo y pedir decisión al usuario.
- Prohibido tocar
docs/kit/**salvo petición explícita del usuario. - No inventar: si falta info →
OPENQ-###y continuar. - Diff-friendly: evita reescrituras masivas; cambia solo lo necesario (anclado a secciones).
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.
- 9d ago First seen · 194 lines · 64 tokens per session scan A 37a0abbdf325
spc-spec-intake 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 64 tokens to every session and 2,213 once invoked, about $0.0003 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.