lade AGENTS.md

lade AGENTS.md is an instructions file for Codex, OpenCode from zifeo/lade. It costs 498 tokens per session, scanned A, original, MPL-2.0.

Project-specific instructions for contributing to lade, a Rust command-line tool. They describe the required checks, code rules, file layout, and behavior that must stay compatible.

In plain words
What is it for?
Use them when changing lade's source, tests, installer, or configuration. They guide commands such as building, testing, linting, shell-script checking, and preserving documented exit codes and JSON output.
Why use it?
They give coding agents the repository's rules in one place, reducing the chance of failed builds, inconsistent messages, or accidental changes to stable command behavior.

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

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 lade AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zifeo/lade/agents-md.svg)](https://agentmods.dev/instructions/zifeo/lade/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zifeo/lade/agents-md"><img src="https://agentmods.dev/badge/instructions/zifeo/lade/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 498 This file is loaded in full into every session.
When invoked 498 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 $0.00498 $0.00498
Opus 5 $0.00249 $0.00249
Sonnet 5 $0.00100 $0.00100
Haiku 4.5 $0.00050 $0.00050

Measured 3d ago against content hash fb13bc41aec3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lade 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 · 49 lines

What it actually says

AGENTS.md

Conventions for AI agents contributing to lade (a Rust CLI). For using lade with coding agents and CI, see the README — this file is about working on the codebase itself.

Build & test

Run these before proposing changes; they must all pass:

cargo build --workspace --locked
cargo test --workspace --locked
cargo clippy --all-targets -- -D warnings
shellcheck installer.sh
bash tests/installer_test.sh

House rules

  • All user-facing stderr goes through message_box::MessageBox — never eprintln!. The box is always emitted; only interactive parts (prompts, countdowns, sleeps) are gated on UiMode (Quiet vs Interactive). See .cursor/rules/message-box.mdc.
  • Never rely on default values; be explicit. Prefer the simplest solution that compiles. Comment only non-obvious intent, not what the code does.
  • Keep documented exit codes (src/exit_codes.rs) stable across minor versions. lade status --json keeps version, global_config, hooks, project_config, and ok; the hooks object is preexec plus pretool.

Project layout

  • src/ — CLI crate. Key modules: pretool/ (lade hook preToolUse handler plus install into Cursor/Claude configs), audience.rs (detect() for Via, Audience, UI), prompt.rs (disclaimer flow), inject.rs/exec/ (PTY execution + masking), status.rs, shell/ (preexec integration), config/, message_box/.
  • sdk/ — the secret-loader crate (vault providers).
  • tests/ — Rust integration tests + installer_test.sh.
  • scripts/, examples/tape/ — shell-hook fixtures and README demo tapes.
  • installer.sh, action.yml, Dockerfile, .github/workflows/ — install & CI surface.

Maintainer note

The GitHub Action (action.yml) is not auto-published to the Marketplace: on each release, tick "Publish this Action to the GitHub Marketplace" in the release UI once.

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 · 49 lines · 498 tokens per session scan A fb13bc41aec3

Subscribe to this mod's changes

lade AGENTS.md is an instructions file published in the GitHub repository zifeo/lade (127 stars, last pushed 13d ago), licensed MPL-2.0. It adds 498 tokens to every session, about $0.0025 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.