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/vertz-dev/vertz/claude-mdgit clone --depth 1 https://github.com/vertz-dev/vertzWhat 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 | $0.00923 | $0.00923 |
| Opus 5 | $0.00462 | $0.00462 |
| Sonnet 5 | $0.00185 | $0.00185 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
vertz 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 yesterday.
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vertz Framework
What is Vertz?
Vertz is a full-stack TypeScript framework. It includes:
- Database ORM (
@vertz/db) — typed queries, migrations, PostgreSQL + SQLite + D1 - API server (
@vertz/server) — entities, services, REST endpoints, auto-generated OpenAPI - Compiled UI (
@vertz/ui) — signals, JSX, router, SSR, forms, scoped CSS - AI agents (
@vertz/agents) — agents, typed tools, workflows on Cloudflare Workers - Custom runtime & CLI (
vtz) — Rust-powered dev server, build, test runner
One schema definition (d.table()) drives the database, API types, client SDK, and UI — if it builds, it works.
Read VISION.md and MANIFESTO.md before making any design decision. Every API, architecture choice, and implementation approach must align with the 8 principles in the vision.
Stack
TypeScript (packages/)
- Runtime: vtz
- Language: TypeScript (strict mode)
- Linter: oxlint
- Formatter: oxfmt
- Test runner:
vtz test - Monorepo: vtz workspaces under
packages/
Rust (native/)
- Language: Rust (2021 edition)
- Linter: clippy
- Formatter: rustfmt
- Test runner:
cargo test - Async runtime: Tokio
- JS engine: V8 via deno_core
- HTTP server: axum
- Cargo workspace under
native/
Development
TypeScript
vtz run build # Build all packages
vtz test # Run tests
vtz run typecheck # TypeScript strict checking
vtz run lint # oxlint check
vtz run lint:fix # Auto-fix lint issues
vtz run format # oxfmt format check
vtz run format:fix # Auto-fix formatting
Rust
cd native
cargo test --all # Run all tests
cargo clippy --all-targets -- -D warnings # Lint
cargo fmt --all -- --check # Format check
cargo fmt --all # Auto-format
cargo build --release # Release build (CI/deploy only, NOT for dev quality gates)
Never use
--releasefor clippy or quality gates during development. Release builds are significantly slower and only needed for CI pipelines and final deployment. Debug mode catches the same lint issues.
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.
- yesterday First seen · 98 lines · 923 tokens per session scan A c3a008869b32
vertz CLAUDE.md is an instructions file published in the GitHub repository vertz-dev/vertz (45 stars, last pushed 4mo ago), licensed MIT. It adds 923 tokens to every session, about $0.0046 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 2026-09-01.
Other instructions, from other repositories
hyperframes AGENTS.md
AGENTS.md instructions for heygen-com/hyperframes, covering hyperframes, skills, build & test, linting & formatting and composition validation.
eve AGENTS.md
Instructions for vercel/eve, covering agents.md, about eve, repository layout, git workflow and commands.
jesse AGENTS.md
Instructions for jesse-ai/jesse, covering jesse repository guide for ai agents, skills, key characteristics, central framework and technology stack.
laravel AGENTS.md
AGENTS.md instructions for laravel/laravel, covering laravel application, prerequisites and agent setup.
AgentEval memory-benchmarks.instructions.md
Guidelines for working with AgentEval Memory module — benchmarks, reporting, HTML reports, and LongMemEval integration.
AgentEval copilot-instructions.md
Instructions for AgentEvalHQ/AgentEval, covering agenteval - ai coding agent instructions, architecture overview, environment setup, optional: secondary models for comparison and build & test commands.