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/llicklair/forja/construyenpx skills add Llicklair/forja --skill construyegit clone --depth 1 https://github.com/Llicklair/forjaWrote 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/llicklair/forja/construye)<a href="https://agentmods.dev/skills/llicklair/forja/construye"><img src="https://agentmods.dev/badge/skills/llicklair/forja/construye.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 5.1 | $0.00169 | $0.02673 |
| Opus 5 | $0.00084 | $0.01337 |
| Sonnet 5 | $0.00034 | $0.00535 |
| Haiku 4.5 | $0.00017 | $0.00267 |
Grade A, and why
construye 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 6d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/construye — Spec-Driven Build verificado (la forja que edifica)
El dual de /forja. La forja REVISA lo que existe; /construye EDIFICA lo que falta desde una
especificación. Misma regla de oro: el loop construye y verifica; NUNCA auto-mergea ni commitea sin
tu OK. Tú decides. El generador no se auto-aprueba: lo verifica un evaluador independiente (otro modelo).
No reinventa la rueda. Adopta GitHub Spec Kit (estándar de facto, ~116k★, nativo en Claude Code) para los artefactos y las fases, y le añade la única parte que no existe como producto en 2026: el motor de verificación cruzada + barrido por-clase + loop continuo bajo nunca-auto-merge de la forja.
La costura (por qué encaja)
/speckit-implement genera código pero deliberadamente NO verifica (su SKILL.md lo dice:
"external verifier handles verification/quality gates"). Ese hueco es el slot de la forja. Y Spec Kit
trae un registro de hooks oficial (.specify/extensions.yml) donde la verificación se cablea sin parchear
nada. /speckit-converge es el bucle brownfield (mapea intención→código, solo añade lo que falta).
| Spec Kit aporta (tal cual) | La forja aporta (el motor) |
|---|---|
| constitution / spec / clarify / plan / tasks | loop driver + cadencia (one-shot o continuo) |
| converge (gaps brownfield, append-only) | test-first de aceptación (DoD ejecutable) |
hooks + [P] (paralelo) + estructura TDD |
generador≠evaluador en otro modelo |
| gate de suite COMPLETA (sin regresión) + checkpoints | |
| barrido por-clase (sin regresión) | |
| worktree · pr/no-pr · nunca auto-merge · gitnexus MARCO |
0. SETUP (detéctalo, no lo hardcodees)
- Spec Kit presente: ¿existe
.specify/y las skills/speckit-*? Si NO →uvx --from git+https://github.com/github/spec-kit.git specify init . --integration claude --script sh. Sin Spec Kit,/construyeno arranca: lo reporta y para. - Sembrar la constitución (
/speckit-constitution): puéblala desdeARCHITECTURE.md+CLAUDE.md+ las reglas rojas del repo. Si el proyecto quiere blindar áreas sensibles, que las declare aquí como principios MUST. La constitución es la LEY que el evaluador hace cumplir (REJECT si se viola). - Gates reales: lee
.github/workflows/*,package.jsonscripts,pyproject.toml [tool.*],Makefiley anota los comandos exactos de lint/type/test/build por subproyecto. - Modo de entrega (igual que la forja):
pr(worktree + PR acumulado) ono-pr(working tree local, sin commitear). "construye con PR" / "construye sin PR" / por defecto, el último. - Seguridad al ejecutar gates (la allowlist NO es sandbox): repo de confianza → auto-ejecuta; repo ajeno sin auditar → sandbox o "verificación no disponible" (a inbox, sin ejecutar).
- GitNexus: si hay grafo, da el MARCO (dónde enchufa la feature) sin meterlo en contexto.
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.
- 6d ago First seen · 120 lines · 169 tokens per session scan A 4ba3bd6e5e81
construye is a skill published in the GitHub repository Llicklair/forja (6 stars, last pushed 2mo ago), licensed MIT. It adds 169 tokens to every session and 2,673 once invoked, about $0.0008 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…