What is advisor AGENTS.md?

A set of instructions for developing and using the Advisor Rust project in Cursor Cloud. It covers setup, building, testing, formatting, linting, and running its command-line tool and web dashboard.

Use it when working on the Advisor repository: install its environment, build or test the code, check formatting and warnings, or run the CLI and dashboard.

It tells an agent which tools and commands apply to this Rust repository and points out outdated Python instructions that should not be followed.

advisor AGENTS.md — Instructions file for Codex and OpenCode by vzwjustin: A set of instructions for developing and using the…

Install

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.

agentmods

npx agentmods add instructions/vzwjustin/advisor/agents-md

Clone the repo

git clone --depth 1 https://github.com/vzwjustin/advisor

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/vzwjustin/advisor/agents-md.svg)](https://agentmods.dev/instructions/vzwjustin/advisor/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/vzwjustin/advisor/agents-md"><img src="https://agentmods.dev/badge/instructions/vzwjustin/advisor/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 409 This file is loaded in full into every session.

When invoked 409 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00409	$0.00409
Opus 5	$0.00204	$0.00204
Sonnet 5	$0.00082	$0.00082
Haiku 4.5	$0.00041	$0.00041

Measured 4d ago against content hash fd11eea0981a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

advisor AGENTS.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.

AGENTS.md · 36 lines

What it actually says

Advisor — Agent Instructions

Cursor Cloud specific instructions

Environment install

The repo on main is Rust-only (advisor-rs / Cargo.toml). There is no pyproject.toml. Use:

bash scripts/setup.sh

Cursor Cloud reads .cursor/environment.json, which runs that script before the agent starts. The script is idempotent (safe to re-run).

Quick reference

Setup / sync deps: bash scripts/setup.sh (or cargo build --locked after toolchain is ready)
Toolchain: rust-toolchain.toml pins stable (needs edition-2024 support — Rust 1.85+)
Build: cargo build
Tests: cargo test --locked
Lint: cargo clippy --all-targets -- -D warnings
Format: cargo fmt --check
All checks: make check (clippy + fmt + test)
Run CLI: cargo run -- <subcommand> (e.g. version, plan, presets, ui)
Web dashboard: cargo run -- ui --port 8765

Gotchas

No Python package on main: tests/*.py and uv sync are legacy; CI uses cargo test --locked.
Zero runtime deps for the binary — only the Rust toolchain is required to build.
Makefile targets wrap cargo (see make help via targets in the Makefile).
The claude and codex CLIs are not needed for development/testing — only for the live pipeline.
If cargo build fails with edition2024 / idna_adapter, run rustup update stable (handled by scripts/setup.sh).

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.

4d ago First seen · 36 lines · 409 tokens per session scan A fd11eea0981a

Subscribe to this mod's changes

advisor AGENTS.md is an instructions file published in the GitHub repository vzwjustin/advisor (10 stars, last pushed 1mo ago), licensed MIT. It adds 409 tokens to every session, about $0.0020 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.

agent-framework ai-agents anthropic claude claude-code cli

kungfu copilot-instructions.md

Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.

kungfu-systems/kungfu · 45 tokens

GPT-RAG release.instructions.md

Instructions for Azure/GPT-RAG, a project described as: Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero-Trust architecture and IaC.

Azure/GPT-RAG · 207 tokens

advisor AGENTS.md