Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add southlab-ai/Claude-Plugin-Marketplace/plugin install repo-ordenWrote 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/southlab-ai/claude-plugin-marketplace/migrar-a-orden)<a href="https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/migrar-a-orden"><img src="https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/migrar-a-orden/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/skills/southlab-ai/claude-plugin-marketplace/migrar-a-orden"><img src="https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/migrar-a-orden.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 | $0.00089 | $0.01477 |
| Opus 5 | $0.00044 | $0.00739 |
| Sonnet 5 | $0.00018 | $0.00295 |
| Haiku 4.5 | $0.00009 | $0.00148 |
Grade A, and why
migrar-a-orden 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 12d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrar un repositorio que ya tiene historia
Instalar la estructura en un repo vacío es trivial. Lo difícil es un repo con 160 documentos donde sesenta se declaran autoridad y cuarenta y nueve mienten — y ahí la tentación es borrar, que es el error.
Antes de tocar nada: mide
El diagnóstico define la solución, y casi siempre sorprende. Mide al menos esto y enséñaselo al usuario:
find docs -name '*.md' | wc -l # cuántos hay
find docs -name '*.md' -exec cat {} + | wc -l # cuánto pesan
grep -rl 'fuente de verdad\|source of truth\|EL CONTRATO' docs/ # cuántos se declaran autoridad
find docs -name '*.md' -mtime +30 | wc -l # cuánto es sedimento
Y lo que de verdad importa: ¿qué de todo eso es ejecutable? Un runbook no se lee, se ejecuta, así que un runbook desactualizado hace daño de verdad. Cruza cada valor que citen contra el sistema vivo.
En un repositorio real esa medición dio: 160 documentos, 42.161 líneas, ~60 autoridades, 49 contradiciendo producción — y los cinco runbooks nombrando releases retirados, ninguno el vivo.
El orden de la migración, y por qué es ese
1 · Arregla la fuente de verdad antes que nada
Si existe un documento que se declara la verdad, compruébalo primero. Suele ser el más desactualizado de todos, precisamente porque todo el mundo confía en él y nadie lo verifica.
Si contiene valores que caducan, no los corrijas a mano: haz que se generen. Un bloque
delimitado que un script rellena preguntándole al sistema, y un --check que falla si dejan de
coincidir.
2 · Instala la estructura
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/bootstrap_orden.py" --en . --dry-run
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/bootstrap_orden.py" --en .
3 · Clasifica lo que ya hay, y usa git mv
La clase la da la carpeta. Para cada documento pregúntate una sola cosa: ¿esto caduca?
| si el documento… | va a |
|---|---|
| describe qué está desplegado ahora | el documento de estado (y se genera) |
| manda sobre el código | contratos/ |
| describe cómo es algo | arquitectura/ |
| explica por qué se decidió algo | adr/ |
| se ejecuta | runbooks/ — y sin un solo valor literal |
| le habla a un consumidor externo | handoff/ |
| lista lo que falta | pendientes/ |
| es el recibo de una medición | evidence/, con la fecha en el nombre |
| es un plan o un charter | planes/ |
| ya pasó y no volverá | archivo/ |
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.
- 12d ago First seen · 132 lines · 89 tokens per session scan A e1ccdd8a166e
migrar-a-orden is a skill published in the GitHub repository southlab-ai/Claude-Plugin-Marketplace (2 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,477 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 skills, from other repositories
cosmergon
Persistent multi-agent economy where autonomous AI agents compete for resources, trade on a marketplace, and benchmark decision-making against a standing population of always-on agents. Invite other agents for energy rewards. Auto-registers — no API key needed.
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…
browser_cdp
A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.