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/jotjunior/cstk/validate-docs-renderednpx skills add JotJunior/cstk --skill validate-docs-renderedgit clone --depth 1 https://github.com/JotJunior/cstkWhat 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 | $0.00067 | $0.01830 |
| Opus 5 | $0.00034 | $0.00915 |
| Sonnet 5 | $0.00013 | $0.00366 |
| Haiku 4.5 | $0.00007 | $0.00183 |
Grade A, and why
validate-docs-rendered 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Validar Renderizacao de Documentacao
Esta skill e uma skill de verificacao de produto (categoria 2 do artigo
original). Ela nao valida se a documentacao esta escrita corretamente — isso e
responsabilidade de validate-documentation e analyze. Ela valida se a
documentacao realmente funciona quando renderizada em GitHub, GitLab,
viewers Markdown, ou outros consumidores downstream.
O gap que ela fecha e o mesmo que o artigo cita: "a diferenca entre doc que passa no review e doc que renderiza corretamente em producao e onde moram os bugs mais caros".
Pre-requisitos
Obrigatorio: diretorio com documentacao Markdown existente (tipicamente
docs/). Se argumento vazio, assume docs/ como default.
Proximos passos
- Corrigir issues reportados (diagramas invalidos, links quebrados)
- Re-rodar a skill para confirmar zero issues
- Considerar rodar como hook pre-commit para prevenir regressao
FLUXO DE EXECUCAO
1. LOCALIZAR Descobrir escopo (arquivo unico ou arvore)
|
2. VALIDAR Rodar scripts de validacao em paralelo
|
3. CLASSIFICAR Agrupar findings por severidade
|
4. REPORTAR Output tabular + exit code
ETAPA 1: LOCALIZAR
Determinar o escopo a partir de $ARGUMENTS:
- Caminho para arquivo (ex:
docs/foo.md): validar apenas esse arquivo - Caminho para diretorio (ex:
docs/02-requisitos-casos-uso/): validar recursivamente - Vazio: assumir
docs/na raiz do projeto
Se o caminho nao existe, abortar com mensagem clara.
ETAPA 2: VALIDAR
Usar o script scripts/validate.sh (mesmo diretorio desta skill). O script
executa 4 validacoes em paralelo onde possivel:
2.1 Diagramas Mermaid
Verifica sintaxe de blocos ```mermaid:
- Participantes declarados antes de uso em
sequenceDiagram - Setas validas (
->>,-->>,->,-->, etc.) - Nos com IDs unicos em
flowchart/graph - Fechamento correto de
alt/else/end,loop/end,par/end - Sintaxe de
erDiagram(relacionamentos, cardinalidade)
What ships with it
2 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.
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 · 209 lines · 67 tokens per session scan A 2867675e81b3
validate-docs-rendered is a skill published in the GitHub repository JotJunior/cstk (22 stars, last pushed 4d ago), licensed MIT. It adds 67 tokens to every session and 1,830 once invoked, about $0.0003 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.
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…