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.
npx agentmods add instructions/xmanatee/pub/agents-mdgit clone --depth 1 https://github.com/xmanatee/pubWhat 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 | $0.00416 | $0.00416 |
| Opus 5 | $0.00208 | $0.00208 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00042 | $0.00042 |
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.
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.
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.
- 2d ago First seen · 44 lines · 416 tokens per session scan A 1aadea411959
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.
Other instructions, from other repositories
gradio AGENTS.md
AGENTS.md instructions for gradio-app/gradio, covering agents.md, repository structure, pull request rules, code style and agentic contribution policy.
web-interface-guidelines AGENTS.md
Instructions for vercel-labs/web-interface-guidelines, covering interactions, keyboard, targets & input, forms and state & navigation.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.