nib AGENTS.md

A project rule telling agents to read the API documentation shipped with the Mobrowser desktop framework before writing framework code. API documentation explains the available functions, types, and usage examples.

In plain words
What is it for?
It helps agents find architecture guides and API references, generate missing documentation when needed, and use verified method signatures and imports.
Why use it?
The framework changes over time, so relying on remembered API names or import paths can produce code that does not compile.

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

Made for: Codex, OpenCode.

Per session 171 This file is loaded in full into every session.
When invoked 171 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 $0.00171 $0.00171
Opus 5 $0.00086 $0.00086
Sonnet 5 $0.00034 $0.00034
Haiku 4.5 $0.00017 $0.00017

Measured 2d ago against content hash 0bb9b3cf4ca5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nib 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 · 15 lines

What it actually says

Read the framework docs before writing code

This app's desktop framework ships its own API docs, and they're more current than any model's training data — its APIs get renamed and reorganized, so code written from memory won't compile.

Before writing or modifying framework code, read the documentation under node_modules/@mobrowser/api/docs/:

  • node_modules/@mobrowser/api/docs/guides/ — architecture, project structure, the multi-process model, IPC, the native module, features, and examples.
  • node_modules/@mobrowser/api/docs/api/ — the API reference with code examples.

Don't guess API names, method signatures, or import paths — look them up in the docs. If the docs/ directory is missing, run npm run gen to download it.

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 · 15 lines · 171 tokens per session scan A 0bb9b3cf4ca5

Subscribe to this mod's changes

nib AGENTS.md is an instructions file published in the GitHub repository caezium/nib (9 stars, last pushed 24d ago), licensed MIT. It adds 171 tokens to every session, about $0.0009 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

higgsfield-ai-prompt-skill CLAUDE.md

Instructions for OSideMedia/higgsfield-ai-prompt-skill, covering claude.md, project overview, tech stack, directory structure and key commands.

OSideMedia/higgsfield-ai-prompt-skill · 1,353 tokens

travel-plan-viz CLAUDE.md

Instructions for zexuanw958-svg/travel-plan-viz, covering claude.md, 这是什么, 架构红线, 测试 and 数据采集约束(写在 references/research-guide.md,改动要同步).

zexuanw958-svg/travel-plan-viz · 2,159 tokens

visual-multimedia AGENTS.md

Instructions for CheshireMew/visual-multimedia, covering visual-multimedia 项目协作规则, 项目定位, 共享边界与唯一真源, 何时必须联动 mediaflow pro and 联动修改规则.

CheshireMew/visual-multimedia · 1,890 tokens

codemap AGENTS.md

Instructions for beadnall/codemap, covering codemap, if you are claude, if you are grok build, if you are another agent and the short version.

beadnall/codemap · 747 tokens

pixeltamer-gpt-image-skill CLAUDE.md

Instructions for gabelul/pixeltamer-gpt-image-skill, covering claude.md — pixeltamer, what this is, architecture, how the skill works and the two backends.

gabelul/pixeltamer-gpt-image-skill · 1,899 tokens

codemap copilot-instructions.md

Instructions for beadnall/codemap: This repository holds a skill for turning a codebase into an explorable isometric diagram. The full instructions are in SKILL.md — read that file and follow it when asked to map, diagram or visually explain how a system fits together.

beadnall/codemap · 325 tokens