rustzen-admin AGENTS.md

A project guide for RustZen Admin, a Rust-based web administration project. It defines which files are authoritative and the rules agents should follow when changing the codebase.

In plain words
What is it for?
Use it to decide what to read first, locate product and architecture information, and follow repository-specific coding and command rules.
Why use it?
It prevents agents from using outdated documentation or crossing boundaries between shared code, backends, frontend code, and deployment files.

Instructions file for CodexOpenCode

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/idaibin/rustzen-admin/agents-md
Clone the repo
git clone --depth 1 https://github.com/idaibin/rustzen-admin

Made for: Codex, OpenCode.

Per session 662 This file is loaded in full into every session.
When invoked 662 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.

ModelPer sessionOnce invoked
Fable 5 $0.00662 $0.00662
Opus 5 $0.00331 $0.00331
Sonnet 5 $0.00132 $0.00132
Haiku 4.5 $0.00066 $0.00066

Measured 3d ago against content hash 630ef14169c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rustzen-admin 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 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.

AGENTS.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Rules

Source of Truth

Reading Order

  1. Read README.md.
  2. Read AGENTS.md.
  3. For product boundary, positioning, direction, or module-purpose decisions, read docs/product/product.md.
  4. Read the nearest subdirectory AGENTS.md.
  5. Read only the relevant guide in docs/guides/.
  6. Use docs/reference/ only for deeper context.

Boundaries

  • RustZen classification: Web/Rust A-class reference layout.
  • Shared auth and permission capability code lives in crates/auth/.
  • Shared Manifest, route, and delegation contracts live in crates/ipc/.
  • Backends live in apps/admin/, apps/monitor/, apps/insights/, and apps/reports/.
  • Each backend owns its migrations under its application directory.
  • Frontend lives in apps/web/.
  • Deployment assets live in deploy/.
  • Root keeps workspace metadata, docs, command entry points, and shared crates.
  • Deployment contract uses one signed target/rz/rz-<version>-<arch>.tar bundle, /opt/rz, deploy/rz.target, deploy/rz-recovery.service, four server units, and deploy/setup-layout.sh.
  • Do not apply Peripheral Vercel, Tauri client, or legacy zen-server / zen-web layout rules to this repository.
  • Do not add systemd User/Group, hardening, or install-path permission changes without reviewing deploy/setup-layout.sh and the /opt runtime directory ownership model together.

Working Rules

  • Prefer the smallest viable change.
  • Use .codex/ as the local task workspace. Keep unfinished cross-session handoffs under .codex/handoffs/<task-id>.md and raw review packages, responses, ledgers, and attachments under .codex/reviews/<review-id>/; both directories are ignored. Put only explicitly requested, sanitized, durable artifacts under docs/.
  • Do not add fallback or compatibility logic.
  • Keep stable product decisions in docs/product/product.md; keep stable implementation facts and rules in docs/architecture.md and docs/guides/.
  • Keep subdirectory AGENTS.md files thin.
  • Do not use docs/reference/ or docs/history/ as default implementation truth.
  • SQLite is the default storage backend.
  • Update code, docs, and commands together when structure changes.
  • Keep task completion tied to the task's verification commands before updating status.

Read the full file on GitHub · 58 lines

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.

  1. 3d ago First seen · 58 lines · 662 tokens per session scan A 630ef14169c8

Subscribe to this mod's changes

rustzen-admin AGENTS.md is an instructions file published in the GitHub repository idaibin/rustzen-admin (171 stars, last pushed 20d ago), licensed Apache-2.0. It adds 662 tokens to every session, about $0.0033 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.