DQIII8: Skill for Claude Code

.claude/skills/svsi/SKILL.md

svsi is a skill for Claude Code from senda-labs/DQIII8. It costs 87 tokens per session (1,188 once invoked), scanned A, original, MIT.

A Spanish-language review workflow for internationalisation reports before they are uploaded to a shared Google Drive folder.

In plain words
What is it for?
Use it to review a named report, suggest focused corrections, or create a handoff for later processing. It is not for regenerating report sections or checking the generation pipeline.
Why use it?
It catches inconsistencies between the questionnaire, diagnosis, and plan that the normal rendering checks may miss.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

This is senda-labs/DQIII8's own configuration. It tells Claude Code how to work on DQIII8 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DQIII8 configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/render_batch.py --slug {slug} --doc-type plan --force.

Part of the dqiii8 plugin — 22 skills, 14 commands, 17 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to senda-labs/DQIII8. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/senda-labs/DQIII8/main/.claude/skills/svsi/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/senda-labs/DQIII8

Made for: Claude Code.

Or install dqiii8, the plugin that ships this one along with the rest of its 22 skills, 14 commands, 17 agents.

Wrote 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.

agentmods badge for svsi

README.md
[![agentmods](https://agentmods.dev/badge/skills/senda-labs/dqiii8/svsi/github.svg)](https://agentmods.dev/skills/senda-labs/dqiii8/svsi)
Your own site
<a href="https://agentmods.dev/skills/senda-labs/dqiii8/svsi"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/svsi/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.

agentmods 80×15 button for svsi

Your own site · 80×15
<a href="https://agentmods.dev/skills/senda-labs/dqiii8/svsi"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/svsi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,188 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00087 $0.01188
Opus 5 $0.00044 $0.00594
Sonnet 5 $0.00017 $0.00238
Haiku 4.5 $0.00009 $0.00119

Measured 11d ago against content hash 119cac25dbc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

svsi 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 11d 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.

.claude/skills/svsi/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/svsi-review — Pre-revisión Semántica de Informes

Proyecto: /root/dqiii8/my-projects/intl-reports/ Reglas/autoridad canónica: my-projects/intl-reports/tools/review/authority.py + my-projects/intl-reports/tests/test_svsi_authority.py + my-projects/intl-reports/tests/test_svsi_invariants.py — no existe un docs/SVSI_PLAN.md separado; el código y su test suite son la única fuente de verdad. Engine: my-projects/intl-reports/tools/review/engine.pyreview_slug(slug) Reporter: my-projects/intl-reports/tools/review/reporter.pywrite_report(report)

Cuándo usar

  • Antes de subir un informe al Drive de ANOVA
  • Cuando un consultor pida verificar un informe específico
  • Para detectar inconsistencias que qa_pre_render existente no captura
  • Trigger explícito: "revisa {slug}", "/svsi-review {slug}", "pre-review {slug}"

Cuándo NO usar

  • Para verificar la generación misma (eso lo hace qa_pre_render dentro del pipeline)
  • Para regenerar secciones (eso requiere tmux externo con core.cli)
  • Para batch overnight (usar my-projects/intl-reports/scripts/pre_drive_review.py desde tmux externo)

Flujo en sesión (Interactive Mode)

Paso 1 — Ejecutar engine:

cd /root/dqiii8/my-projects/intl-reports
python3 -c "
from tools.review.engine import review_slug
from tools.review.reporter import write_report
report = review_slug('{slug}')
write_report(report)
print(f'Verdict: {report.summary[\"verdict\"]}  C={report.summary[\"critical\"]}  H={report.summary[\"high\"]}  issues={len(report.issues)}')
"

Paso 2 — Leer report estructurado:

cat companies/{slug}/review/review_report.json

Paso 3 — Para cada issue, según remediation:

remediation Acción en sesión
surgical_edit Proponer Edit usando edit_hint.path + edit_hint.new_template. Pedir confirmación. Aplicar.
regen_section Mostrar handoff_command. Escribir data/svsi_handoff_{slug}.txt. NO ejecutar.
human_review Mostrar al usuario para decisión manual del consultor ANOVA.
dismiss_only Mostrar como informativo. Preguntar si registrar como FP.

Read the full file on GitHub · 115 lines

Changes

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.

  1. 11d ago First seen · 115 lines · 87 tokens per session scan A 119cac25dbc6

Subscribe to this mod's changes

svsi is a skill published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 22d ago), licensed MIT. It adds 87 tokens to every session and 1,188 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 2026-08-30.

Related

Other skills, from other repositories