pub AGENTS.md

Project instructions for Pub, a full-stack TypeScript system for interfaces powered by AI agents, including its web app, command-line tool, relay services, and live app.

In plain words
What is it for?
They guide work across the monorepo, including its app, CLI, relay, live chat, canvas, tunnel, bridge, configuration, and generated files.
Why use it?
They help developers make changes in the correct system layer without overwriting user content or breaking privacy and cleanup rules.

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

Made for: Codex, OpenCode.

Per session 416 This file is loaded in full into every session.
When invoked 416 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 $0.00416 $0.00416
Opus 5 $0.00208 $0.00208
Sonnet 5 $0.00083 $0.00083
Haiku 4.5 $0.00042 $0.00042

Measured 2d ago against content hash 1aadea411959, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pub 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 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.

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 · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pub

Pub is a full-stack TypeScript system for adaptive interfaces powered by AI agents. The repo spans a web app, CLI, relay infrastructure, and an embedded live app experience.

Before broad work, read parent AGENTS.md files up to the mono root; nearest scoped instructions apply last.

Operating Principles

  • Treat the implementation, configuration schema, package scripts, and focused docs as the source of truth for exact commands, protocols, limits, and wiring.
  • Keep agent-facing guidance high level here; do not duplicate details that can be read directly from code, generated config, or narrower documentation.
  • Preserve user-owned workspaces and user-authored content. Initialization and upgrades must not silently overwrite local edits.
  • Keep live chat, canvas, tunnel, and bridge responsibilities separated. Do not route around the owning layer when changing delivery behavior.
  • Keep generated, vendored, and primitive UI surfaces read-only unless their owning workflow explicitly regenerates or updates them.
  • Follow existing routing, state, styling, and data-ownership patterns before introducing new abstractions.
  • Keep product privacy and cleanup invariants intact when adding creation, sharing, connection, or deletion behavior.
  • When public CLI or agent-facing behavior changes, keep the shipped runtime guidance and metadata in sync with the implementation.

Architecture Guidelines

  • Web, CLI, relay, and live-app code should remain loosely coupled through their existing boundaries.
  • The CLI owns local setup, validation, daemon lifecycle, bridge coordination, and tunnel startup. Keep those concerns explicit and observable.
  • The embedded live app is a starting point for user work. Once materialized in a workspace, treat it as user-owned source.
  • Feature work should be additive where possible and should keep feature-local concerns inside the feature boundary.
  • Prefer small, verifiable changes that preserve established conventions over broad refactors.

Read the full file on GitHub · 44 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. 2d ago First seen · 44 lines · 416 tokens per session scan A 1aadea411959

Subscribe to this mod's changes

pub AGENTS.md is an instructions file published in the GitHub repository xmanatee/pub (2 stars, last pushed 2mo ago), licensed MIT. It adds 416 tokens to every session, about $0.0021 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.

Related

Other instructions, from other repositories