looper_rust AGENTS.md

looper_rust AGENTS.md is an instructions file for Codex, OpenCode from quangdang46/looper_rust. It costs 539 tokens per session, scanned A, original, MIT.

Project instructions for looper_rust, a Rust codebase organized into related packages called crates. They list commands for building, testing, formatting, linting, and checking the workspace, which is the full group of packages.

In plain words
What is it for?
Making and verifying changes in looper_rust, either across the whole workspace or within one named crate.
Why use it?
They give coding agents the repository’s expected commands and show how its crates are divided into areas such as storage, scheduling, GitHub access, and agent execution.

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/quangdang46/looper_rust/agents-md
Clone the repo
git clone --depth 1 https://github.com/quangdang46/looper_rust

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.

agentmods badge for looper_rust AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/quangdang46/looper_rust/agents-md.svg)](https://agentmods.dev/instructions/quangdang46/looper_rust/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/quangdang46/looper_rust/agents-md"><img src="https://agentmods.dev/badge/instructions/quangdang46/looper_rust/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 539 This file is loaded in full into every session.
When invoked 539 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 $0.00539 $0.00539
Opus 5 $0.00269 $0.00269
Sonnet 5 $0.00108 $0.00108
Haiku 4.5 $0.00054 $0.00054

Measured 3d ago against content hash e87dcb3a17c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

looper_rust 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 · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Looper Rust — AI Agent Guidelines

Build

cargo build --release          # Release build (all targets)
cargo build                    # Debug build
cargo check --workspace        # Fast type-check (recommended during dev)

Test

cargo test --workspace         # All tests
cargo test -p <crate>          # Single crate
cargo test -p <crate> -- <name> # Single test by name

Lint

cargo fmt --check              # Format check
cargo fmt                      # Auto-format
cargo clippy --workspace -- -D warnings  # Full lint
cargo clippy -p <crate>        # Single crate

Workspace Members

Crate Type Description
looper-types lib Domain enums, state machines, core types
looper-config lib Config loading, validation, merge, disclosure
looper-storage lib SQLite repositories, migrations, event log
looper-service lib Loop, Run, Project business logic
looper-github lib GitHub gateway via gh CLI
looper-git lib Git worktree management
looper-agent lib Agent executor (5 vendors)
looper-scheduler lib Tick loop, queue claim, discovery
looper-runner lib Planner, Reviewer, Fixer, Worker, Coordinator
looper-api lib axum REST server, auth, envelope
looper-webhook lib Webhook forwarder, event routing
looper-infra lib Bootstrap, runtime, notifications
looperd bin Daemon binary
looper-cli bin CLI binary
looper-net bin Loopernet cloud server binary
diffanchor lib Diff parsing and anchor validation

Directory Layout

looper_rust/
├── Cargo.toml                 # Workspace root
├── crates/                    # All crates
│   ├── looper-types/          # Phase 1
│   ├── looper-config/         # Phase 2
│   ├── ...
├── legacy/                    # Go reference (gitignored)
├── PORTING-TO-RUST/
│   ├── LOOPER_RUST_DESIGN.md  # Architecture design
│   └── specs/                 # Behavioral specs
├── .github/workflows/         # CI/CD
└── .beads/                    # Task tracking

Read the full file on GitHub · 65 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 · 65 lines · 539 tokens per session scan A e87dcb3a17c4

Subscribe to this mod's changes

looper_rust AGENTS.md is an instructions file published in the GitHub repository quangdang46/looper_rust (4 stars, last pushed 15d ago), licensed MIT. It adds 539 tokens to every session, about $0.0027 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.