Borrowing it
Nothing to install: this file belongs to pedrobraiti/vizier-trading-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pedrobraiti/vizier-trading-skill/main/CLAUDE.mdgit clone --depth 1 https://github.com/pedrobraiti/vizier-trading-skillWrote 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/instructions/pedrobraiti/vizier-trading-skill/claude-md)<a href="https://agentmods.dev/instructions/pedrobraiti/vizier-trading-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/pedrobraiti/vizier-trading-skill/claude-md/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/instructions/pedrobraiti/vizier-trading-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/pedrobraiti/vizier-trading-skill/claude-md.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 | $0.01449 | $0.01449 |
| Opus 5 | $0.00724 | $0.00724 |
| Sonnet 5 | $0.00290 | $0.00290 |
| Haiku 4.5 | $0.00145 | $0.00145 |
Grade A, and why
vizier-trading-skill CLAUDE.md 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instruções para o Claude neste projeto
VIZIER — o cérebro do trio agentic-trading. Skill
/vizierque orquestra Scout (sentidos/dados) e Valet (mãos/execução). Ler.claude/context.mdedocs/SPEC-origin.mdpara o panorama completo.
Fronteira inviolável (regra nº1 deste projeto)
A skill consome Scout e Valet exatamente como eles são. NUNCA adiciona, modifica ou "pluga" nada dentro de Scout ou Valet — os dois são MCPs independentes. Toda inteligência, cola, estado e decisão mora NA SKILL. Nenhum MCP chama o outro; nenhum MCP conclui. Se a skill precisar de algo que nenhum MCP entrega, resolve na skill (helper Python ou prompt), jamais embutindo lógica nos MCPs.
Código público / estado privado
O repo desta skill será público (terceiro do trio). Mas a memória de trading real
(memory/theses/*.yaml, memory/decision_log.jsonl, snapshots de NAV) é gitignored — posições e
decisões reais NUNCA vão pro GitHub. Só templates/exemplos são commitados. Espelha o .env gitignored dos MCPs.
Memória persistente
Ao iniciar qualquer conversa neste projeto, antes de agir:
- Leia
.claude/handoff.mdPRIMEIRO — é o ponteiro mais fresco: responde "de onde parei" com detalhe. - Leia
.claude/context.mdpara o estado macro/estável do projeto. - Leia
.claude/todo.mdpara saber o que está em progresso e o que vem a seguir. - Rode
git log --oneline -20para ver atividade recente. - Se a tarefa tocar em área sensível/arquitetural, leia
.claude/decisions.md.
Manter o handoff vivo
O .claude/handoff.md é o que permite a próxima sessão começar de onde esta parou. Trate-o como documento vivo:
- Ao concluir qualquer passo significativo (não só no fim da sessão), atualize-o.
- Escreva com detalhe suficiente para um chat novo retomar sem reconstruir seu raciocínio: onde parou, o contexto mental, o próximo passo concreto e o que está em aberto.
- Atualize a data e sobrescreva o conteúdo antigo — ele reflete sempre o ESTADO ATUAL de "onde paramos", não é histórico append-only (esse papel é do git e do
decisions.md).
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 · 85 lines · 1,449 tokens per session scan A 4b74a4ecb13a
vizier-trading-skill CLAUDE.md is an instructions file published in the GitHub repository pedrobraiti/vizier-trading-skill (7 stars, last pushed 5d ago), licensed MIT. It adds 1,449 tokens to every session, about $0.0072 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).