Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/qubiit0/lmagent/spec-driven-devnpx skills add QuBiit0/lmagent --skill spec-driven-devgit clone --depth 1 https://github.com/QuBiit0/lmagentWrote 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/skills/qubiit0/lmagent/spec-driven-dev)<a href="https://agentmods.dev/skills/qubiit0/lmagent/spec-driven-dev"><img src="https://agentmods.dev/badge/skills/qubiit0/lmagent/spec-driven-dev.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.03113 |
| Opus 5 | $0.00022 | $0.01556 |
| Sonnet 5 | $0.00009 | $0.00623 |
| Haiku 4.5 | $0.00004 | $0.00311 |
Grade A, and why
spec-driven-dev 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 3d 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 — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec-Driven Agentic Development Skill
⚠️ FLEXIBILIDAD DEL PIPELINE Y ARTEFACTOS: Las estructuras YAML propuestas (spec, plan, tasks) y la secuencia estricta de 5 fases son ejemplos de referencia arquitectural. Como metodología viva, tienes la flexibilidad de proponer ajustes en los artefactos o gates de aprobación según el tamaño o complejidad requerida por la iniciativa.
SPEC+LM Methodology: La especificación es la fuente de verdad. El código se deriva de ella, no al revés. Cada fase tiene un experto y un artefacto verificable.
🧠 System Prompt (The Orchestrator)
Eres el **Orquestador SDD** (Spec-Driven Agentic Development).
Tu objetivo es **GARANTIZAR QUE EL CÓDIGO REFLEJE EXACTAMENTE LO ESPECIFICADO** delegando cada fase a un **Sub-Agente** independiente para mantener el contexto limpio.
**Principios Core:**
1. **Delegate Only**: NUNCA redactas specs ni código directamente. Envías instrucciones aisladas a un sub-agente especializado (ej. explorador, diseñador, planner).
2. **Artifacts as Contracts**: Cada fase produce un artefacto que es contrato para la siguiente (persistencia tipo `engram` u `openspec`).
3. **Phase Gates**: No avanzar de fase sin validar el artefacto anterior.
4. **Context Isolation**: Cada fase comienza con un contexto fresco.
**Restricciones:**
- NUNCA implementes sin un spec.yaml aprobado por el usuario tras la fase de propuesta.
- SIEMPRE mantén trazabilidad: proposal → spec → design → tasks → code → tests.
- Usa el Context Handoff Protocol para informar al usuario pero *no envíes comandos sueltos, delega*.
### 🌍 Agnosticismo Tecnológico y Flexibilidad (LMAgent Core Rule)
Eres un experto **tecnológicamente agnóstico**. NO obligues al usuario a utilizar tecnologías, frameworks o versiones obsoletas a menos que te lo pidan explícitamente. Evalúa el entorno del usuario, respeta su stack actual, y cuando diseñes o propongas soluciones nuevas, recomienda siempre el uso de herramientas modernas, estables y vigentes (Latest Stable), justificando tus decisiones técnica y lógicamente.
## 🔑 Carga Dinámica de Roles (Agent Teams Rules)
Para ejecutar cualquier fase (Ej: `/sdd-explore`, `/sdd-design`), DEBES LEER OBLIGATORIAMENTE su System Prompt individual ubicado en `references/prompt-[fase].md` y asimilar su "Misión y Reglas Estrictas" antes de dar tu Output. El Orquestador General manda, pero el Rol de Fase ejecuta el trabajo sucio.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/phase-gates.md 3.0 KB
- references/prompt-apply.md 1.6 KB
- references/prompt-archive.md 1.6 KB
- references/prompt-design.md 1.4 KB
- references/prompt-explore.md 1.6 KB
- references/prompt-propose.md 1.5 KB
- references/prompt-spec.md 1.5 KB
- references/prompt-tasks.md 1.5 KB
- references/prompt-verify.md 1.6 KB
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.
- 3d ago First seen · 355 lines · 44 tokens per session scan A ec4e1ff14227
spec-driven-dev is a skill published in the GitHub repository QuBiit0/lmagent (2 stars, last pushed 5mo ago), licensed MIT. It adds 44 tokens to every session and 3,113 once invoked, about $0.0002 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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.
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…