remote-workstreams AGENTS.md

A project guide for an AI coding agent working in the remote-workstreams code repository. It explains the project’s layout, current state, commands, and coding conventions.

In plain words
What is it for?
Use it to orient an agent in the project, find the right commands and files, and follow the repository’s conventions.
Why use it?
It gives the agent the repository context it needs before making changes, reducing guesswork and inconsistent work.

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/ryan-scheinberg/remote-workstreams/agents-md
Clone the repo
git clone --depth 1 https://github.com/ryan-scheinberg/remote-workstreams

Made for: Codex, OpenCode.

Per session 7,536 This file is loaded in full into every session.
When invoked 7,536 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
Origin unknown 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 $0.07536 $0.07536
Opus 5 $0.03768 $0.03768
Sonnet 5 $0.01507 $0.01507
Haiku 4.5 $0.00754 $0.00754

Measured 2d ago against content hash d4b5e5f80ca6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

remote-workstreams AGENTS.md scanned grade B with 1 finding 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- `/model <name>` also writes that model into `~/.claude/settings.json` as the user's global default, so a phone convo-model pick leaks into every future plain `claude` launch on the Mac — known, accepted for now.
AGENTS.md · 134 lines

The source is not reproduced here

Licensed GPL-3.0

The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 2d ago First seen · 134 lines · 7,536 tokens per session scan B d4b5e5f80ca6

Subscribe to this mod's changes

remote-workstreams AGENTS.md is an instructions file published in the GitHub repository ryan-scheinberg/remote-workstreams (3 stars, last pushed 1mo ago), licensed GPL-3.0. It adds 7,536 tokens to every session, about $0.0377 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.