What is zdx AGENTS.md?

A workspace guide for zdx, a Rust monorepo—a repository containing several related packages—with a central product specification and separate instructions for each package.

It is for navigating the repository and developing its terminal interface, monitoring tools, language-model providers, orchestration engine, shared transcript handling, and embedded assets.

It helps the coding agent find the right package and follow the correct conventions when changing shared types, providers, tools, the engine, or user interfaces.

How tallesborges/zdx configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to tallesborges/zdx. 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/tallesborges/zdx/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/tallesborges/zdx

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/tallesborges/zdx/agents-md/github.svg)](https://agentmods.dev/instructions/tallesborges/zdx/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/tallesborges/zdx/agents-md"><img src="https://agentmods.dev/badge/instructions/tallesborges/zdx/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tallesborges/zdx/agents-md"><img src="https://agentmods.dev/badge/instructions/tallesborges/zdx/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,777 This file is loaded in full into every session.

When invoked 2,777 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.

Model	Per session	Once invoked
Fable 5.1	$0.02777	$0.02777
Opus 5.5	$0.01111	$0.01111
Sonnet 5.5	$0.00555	$0.00555
Haiku 4.5	$0.00278	$0.00278

Measured yesterday against content hash eea8469df4d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zdx 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 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.

AGENTS.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

zdx workspace development guide

docs/SPEC.md is the source of truth for product behavior (contracts). This file is the workspace index.

AGENTS.md index

This monorepo now uses scoped AGENTS.md files per crate.

AGENTS.md (this file): workspace-level conventions + index
crates/zdx-assets/AGENTS.md: embedded assets (prompts, default TOMLs, bundled skills, built-in subagents)
crates/zdx-types/AGENTS.md: pure shared value types and pure helper logic for providers, tools, events
crates/zdx-transcript/: shared transcript display model + rendering (thread events → HistoryCells → styled/ratatui lines; markdown, wrapping, tool pairing, tool_detail_body for full tool args/output) plus shared TUI interaction utilities (clipboard with OSC 52 → arboard fallback, keys::GPrefix vim gg prefix). Reused by zdx-tui and zdx-monitor.
crates/zdx-providers/AGENTS.md: LLM provider implementations (Anthropic, OpenAI, Gemini, etc.)
crates/zdx-engine/AGENTS.md: core engine — runtime, config, agent orchestration, tools
crates/zdx-tui/AGENTS.md: TUI architecture map + runtime/features conventions
crates/zdx-tools/AGENTS.md: leaf tool implementations (bash, edit, read, write, glob, grep, web_search, fetch_webpage, apply_patch)
crates/zdx-cli/AGENTS.md: CLI routing/modes/commands map + CLI testing guidance
crates/zdx-bot/AGENTS.md: Telegram bot flow map + bot-specific conventions
crates/zdx-monitor/AGENTS.md: monitor TUI dashboard map + conventions
crates/xtask/AGENTS.md: maintainer task crate guidance
apps/web/AGENTS.md: Svelte Mini App frontend (design system + views, consumes the zdx-bot HTTP API)

Scope and precedence

AGENTS.md applies to its directory tree.
For each changed file, follow every in-scope AGENTS.md.
When rules conflict: deeper AGENTS.md wins; system/developer/user instructions win over all AGENTS.md.
Scope-specific style rules stay within scope unless explicitly stated otherwise.
If an in-scope AGENTS.md requires checks, run them after changes and make a best effort to pass.

Read the full file on GitHub · 147 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.

yesterday Changed · +1 lines · +24 tokens per session eea8469df4d4
3d ago Changed · +1 lines · +21 tokens per session 4af140702d05
7d ago Changed · +3 lines · +74 tokens per session 1073340c499d
13d ago Changed · +1 lines · +93 tokens per session 8eba3a53bf51
1mo ago Changed · +18 lines · +237 tokens per session 6204cb89c36b
1mo ago Changed · +3 lines · +230 tokens per session 1ad09fb8bb68
1mo ago Changed · +3 lines · +101 tokens per session bc5b68d98893
1mo ago First seen · 117 lines · 1,997 tokens per session scan A c66129b346cd

Subscribe to this mod's changes

zdx AGENTS.md is an instructions file published in the GitHub repository tallesborges/zdx (20 stars, last pushed yesterday), licensed MIT. It adds 2,777 tokens to every session, about $0.0111 per session on Opus 5.5. 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.

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 · 9,715 tokens

zdx: Instructions file for Codex

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

zdx workspace development guide

AGENTS.md index

Scope and precedence

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

vscode oss-third-party-notices.instructions.md

langchain AGENTS.md

vscode copilot-instructions.md

vscode model-prompts.instructions.md