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-director.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-director)<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.
<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>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 | $0.00072 | $0.03363 |
| Opus 5 | $0.00036 | $0.01682 |
| Sonnet 5 | $0.00014 | $0.00673 |
| Haiku 4.5 | $0.00007 | $0.00336 |
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.
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):
- El Director pregunta directamente al usuario (2 preguntas por turno).
- Tras cada respuesta, acumula contexto internamente.
- 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."
- Pide confirmación al usuario.
- Delega a
spc-spec-intakeprogramáticamente en one-shot, pasándole todo el contexto acumulado para que formalice00-context.md,95-open-questions.mdy gates. - 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).
- El Director propone: "He detectado un codebase con contenido. Para planificar bien, conviene mapear el proyecto primero. ¿Discovery rápido, profundo, o lo salto?"
- Si acepta → delega a
spc-codebase-discovery(MODE=initial, DEPTH=quick|deep). - Si rechaza → registra en
00-context.md: "Discovery: omitido por decisión del usuario (fecha)." - 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-intakecon contexto ampliado.
- Presenta resultados (mapa, EPs, OPENQs) y continúa hacia Fase 2.
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.
- 10d ago First seen · 216 lines · 72 tokens per session scan A 277079ba3b4a
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.
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.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.