Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Mazalucas/El-DT-Lightweight-Armynpx agentmods add skills/mazalucas/el-dt-lightweight-army/dt-oficialWrote 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/mazalucas/el-dt-lightweight-army/dt-oficial)<a href="https://agentmods.dev/skills/mazalucas/el-dt-lightweight-army/dt-oficial"><img src="https://agentmods.dev/badge/skills/mazalucas/el-dt-lightweight-army/dt-oficial/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/mazalucas/el-dt-lightweight-army/dt-oficial"><img src="https://agentmods.dev/badge/skills/mazalucas/el-dt-lightweight-army/dt-oficial.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 | $0.00032 | $0.00514 |
| Opus 5.5 | $0.00013 | $0.00206 |
| Sonnet 5.5 | $0.00006 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
dt-oficial 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 1mo 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.
What it actually says
dt-oficial
Spec: vitals/specs/canonical-publish.md.
Por defecto ninguna carpeta publica al DT. Este comando escribe una marca local, gitignored, en la carpeta que el dueño confirma.
Lo que se publica es el framework. No viaja la sesión, el roster con personas, la postura de esta máquina ni el cuaderno vitals/work/inbox/. roster.yaml en Git se queda con team: []. Si el gate sale 50, esos rastros están en el árbol: no se commitean.
Invocaciones
| Comando | Acción |
|---|---|
/oficial |
Mostrar la ruta y pedir confirmación. Sin el sí, no marcar. |
/oficial y en el mismo mensaje ya confirmaron esta ruta |
Activar |
/oficial off |
Borrar la marca |
/oficial status |
Decir si esta carpeta puede publicar |
Activar
-
Corré sin escribir la marca:
./scripts/dt-oficial.sh activate -
Si el exit es 2, mostrale al usuario la carpeta, el
originy el login, y preguntá: ¿Marco esta carpeta como el checkout oficial del DT? Esperá el sí. No pases--yesen el mismo turno salvo que ese mensaje ya haya confirmado esa ruta. -
Con el sí:
./scripts/dt-oficial.sh activate --yes -
Exit 0 y la salida ya dice que el checkout está activo: no vuelvas a preguntar.
-
Exit 1: mostrá el motivo y pará. No ofrezcas pedir acceso, ni invitación, ni
gh authpara publicar el DT con otra cuenta.
Apagar
./scripts/dt-oficial.sh off
No hacer
- No marcar una carpeta distinta de la que muestra el script.
- No copiar
vitals/ops/canonical-checkout.yamla otro clone. - No commitear ese archivo.
- No tratar
mode: canonicalni/yocomo sustituto de este comando.
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.
- 1mo ago First seen · 53 lines · 32 tokens per session scan A a8d8bac6a184
dt-oficial is a skill published in the GitHub repository Mazalucas/El-DT-Lightweight-Army (4 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 514 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-24.
Other skills, from other repositories
github-release-management
GitHub release orchestration — automated versioning, testing, deployment, and rollback. Use when cutting a release, tagging a version, drafting release notes, or coordinating a deploy/rollback workflow.
new-gh-issue-orchestration
Orchestrates a GitHub-issue-driven delivery workflow from issue intake to PR creation using reviewer-first then worker execution. Invoked when the user provides a GitHub issue link/number and asks to start end-to-end delivery.
dale-loop-pr
Monitor or repair one existing pull request using current review and CI evidence. Use for PR babysitting, scoped fixes, or carrying a PR to merge-ready state.
dale-loop-repo
Maintain a repository on a requested recurring cadence using bounded priorities and live evidence. Use for recurring engineering triage or repository maintenance.
agentic-jujutsu
Use when multiple agents need to write to the same repo concurrently without file-lock stalls — applies claim-before-write, parallel branch fan-out, and semantic 3-way merge to achieve 87% auto-conflict resolution.
session-checkpoint
Use when you want to save a timestamped snapshot of current session state (tasks, evidence, purpose) to docs/session-logs/ for crash recovery or handoff.