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 instructions/pedrogiudice/lex-vector/claude-mdgit clone --depth 1 https://github.com/PedroGiudice/lex-vectorWrote 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/pedrogiudice/lex-vector/claude-md)<a href="https://agentmods.dev/instructions/pedrogiudice/lex-vector/claude-md"><img src="https://agentmods.dev/badge/instructions/pedrogiudice/lex-vector/claude-md.svg" alt="Measured on agentmods" 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 | $0.00893 | $0.00893 |
| Opus 5 | $0.00447 | $0.00447 |
| Sonnet 5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
lex-vector 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 4d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
PORTUGUES BRASILEIRO COM ACENTUACAO CORRETA. Acentos sao obrigatorios: e, a, a, c, etc.
Instrucoes operacionais para Claude Code neste repositorio.
Arquitetura: ARCHITECTURE.md (North Star)
Regras deste Repositorio
1. Bun OBRIGATORIO para frontend (nunca npm/yarn)
bun install && bun run dev
2. uv OBRIGATORIO para Python (nunca pip)
cd legal-workbench/ferramentas/legal-text-extractor && uv sync
3. Testes antes de commit
# ferramentas (pre-commit executa ruff + pytest)
cd legal-workbench/ferramentas/legal-text-extractor && uv run pytest
4. Tauri: sincronizar versoes
Cargo.toml e tauri.conf.json DEVEM ter a mesma versao. Verificar ambos antes de build.
5. ZERO Emojis
PROIBIDO em qualquer output. Bug no CLI Rust causa crash em char boundaries (4 bytes).
Erros Aprendidos
Adicione entrada quando: usuario corrigir erro seu, erro grosseiro, ou erro repetido.
| Data | Erro | Regra |
|---|---|---|
| 2026-01-11 | Emoji causou crash do CLI | Regra #5: ZERO emojis |
| 2026-01-11 | Crash pode perder edits nao commitados | Commitar frequentemente |
| 2026-01-13 | Troquei modelo especificado pelo usuario | NUNCA substituir modelo indicado |
| 2026-01-17 | Build local nao atualiza Docker | Docker faz build interno, rsync nao basta |
| 2026-01-17 | Assumi deps erradas do LTE | VER CLAUDE.md do modulo antes de rodar testes |
| 2026-01-31 | Versao Cargo.toml divergia de tauri.conf.json | Regra #4: sincronizar versoes |
| 2026-03-05 | Estimativas teoricas de RAM/storage sem validar | WebSearch e WebFetch ANTES de estimar recursos |
| 2026-03-05 | Nao usei WebSearch para validar sizing de Qdrant | WebSearch e WebFetch sao ferramentas poderosas -- usar ANTES de estimar |
| 2026-03-05 | Assumi VRAM do Marker sem dados ("~4-6GB pico numa T4") | NAO assumir metricas de hardware sem medir ou pesquisar primeiro |
| 2026-03-05 | Adicionei volume_data.commit() dentro de container paralelo no Modal | NUNCA commit() dentro de containers .spawn() -- causa race condition (last-write-wins). Commit apenas via flush_volume() no final |
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.
- 4d ago First seen · 87 lines · 893 tokens per session scan A 2ce21d40a59c
lex-vector CLAUDE.md is an instructions file published in the GitHub repository PedroGiudice/lex-vector (5 stars, last pushed 3mo ago), licensed MIT. It adds 893 tokens to every session, about $0.0045 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
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.