beads-rs: Instructions file for Codex

AGENTS.md

beads-rs AGENTS.md is an instructions file for Codex, OpenCode from delightful-ai/beads-rs. It costs 3,632 tokens per session, scanned A, original, MIT.

Repository guidance for beads-rs, a Rust-based database for shared work items that uses Git to synchronize changes between agents. It explains the project’s architecture, design rules, and key commands.

In plain words
What is it for?
Use it when modifying beads-rs, especially its data model, merge rules, daemon, command-line interface, or Git synchronization logic.
Why use it?
It gives coding agents the project’s working model and constraints before they change code, reducing inconsistent designs and broken synchronization behavior.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is delightful-ai/beads-rs's own configuration. It tells Codex and OpenCode how to work on beads-rs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything beads-rs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to delightful-ai/beads-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/delightful-ai/beads-rs/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/delightful-ai/beads-rs

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 beads-rs AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/delightful-ai/beads-rs/agents-md/github.svg)](https://agentmods.dev/instructions/delightful-ai/beads-rs/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/delightful-ai/beads-rs/agents-md"><img src="https://agentmods.dev/badge/instructions/delightful-ai/beads-rs/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for beads-rs AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/delightful-ai/beads-rs/agents-md"><img src="https://agentmods.dev/badge/instructions/delightful-ai/beads-rs/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,632 This file is loaded in full into every session.
When invoked 3,632 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.03632 $0.03632
Opus 5 $0.01816 $0.01816
Sonnet 5 $0.00726 $0.00726
Haiku 4.5 $0.00363 $0.00363

Measured 9d ago against content hash c395a3af094e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

beads-rs 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 9d 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 · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

beads-rs

Distributed work-item database for agent swarms, using git as the sync layer. Rust rewrite of the original Go beads.

Core idea: beads are a CRDT. Most fields are last-writer-wins via Lww<T> (timestamp + actor); merges are deterministic. State syncs through refs/heads/beads/store, separate from code branches.

A local daemon holds canonical state and schedules git sync (~500ms). CLI talks to it over Unix socket, auto-starts on first use. One daemon serves many clones by keying state on normalized remote URL.

If this is your first time touching beads this session, run bd prime. It is the fastest way to reload the mental model and command language.

Worldview

  • Kill scatter: One source of truth per concept. If data lives in two places, merge or derive.
  • Types tell the truth: Typed digests, enums not strings, validated IDs. Wrong states should be unrepresentable.
  • Proof beats vibes: deterministic merges, explicit invariants, and cheap verification are part of the design, not cleanup.

Architecture

The important ownership split is:

crates/beads-core/         Canonical domain model, CRDT semantics, validated types, apply/merge rules
crates/beads-api/          Output/result schemas for CLI/daemon JSON surfaces
crates/beads-bootstrap/    Repo discovery, path derivation, config schema + precedence
crates/beads-surface/      IPC request/response contract, client helpers, shared patch/query types
crates/beads-cli/          Command language, clap parsing, request construction, human/JSON rendering
crates/beads-git/          Git-backed sync, wire format, checkpoint import/export/publication
crates/beads-daemon-core/  Shared REPL/WAL/durability contracts
crates/beads-daemon/       Runtime process, store/session lifecycle, mutation/query orchestration
crates/beads-rs/           Assembly crate/package entrypoint, host seams, binary wiring, upgrade/migration glue
crates/beads-rs/tests/     Assembly/product integration, package behavior, public-boundary enforcement
scripts/                   Side-effectful tooling, profiling helpers, release/install automation
docs/                      Source-of-truth specs, design notes, and repo policy documents
lints/                     Custom Dylint rules and vendored lint authoring utilities

Read the full file on GitHub · 249 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. 9d ago First seen · 249 lines · 3,632 tokens per session scan A c395a3af094e

Subscribe to this mod's changes

beads-rs AGENTS.md is an instructions file published in the GitHub repository delightful-ai/beads-rs (24 stars, last pushed 20d ago), licensed MIT. It adds 3,632 tokens to every session, about $0.0182 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens