INSTRUCTIONS

Shared instructions for AI coding agents working in Nex repositories. They keep tool-specific files such as CLAUDE.md and AGENTS.md connected to one canonical instruction file.

In plain words
What is it for?
Use it to maintain equivalent instructions for Claude, Codex, and other agents across Nex repositories.
Why use it?
It prevents different coding agents from receiving conflicting repository guidance.

Agent

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 agents/najmuzzaman-mohammad/gawkbot/instructions
Clone the repo
git clone --depth 1 https://github.com/najmuzzaman-mohammad/gawkbot
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,160 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.07160
Opus 5 $0.00000 $0.03580
Sonnet 5 $0.00000 $0.01432
Haiku 4.5 $0.00000 $0.00716

Measured yesterday against content hash fb5b27b49744, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

INSTRUCTIONS 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 yesterday.

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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

heavy mocking for little signal — do it and move on. Don't lecture.
docs/agents/INSTRUCTIONS.md · 637 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

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. yesterday First seen · 637 lines · 0 tokens per session scan B fb5b27b49744

Subscribe to this mod's changes

INSTRUCTIONS is an agent published in the GitHub repository najmuzzaman-mohammad/gawkbot (1,247 stars, last pushed 2d ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 7,160 tokens. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

library_book_renewal.sop

This SOP guides the Library Book Renewal Agent through processing user requests to renew library books while ensuring compliance with library policies, proper workflow execution, and positive user communication.

strands-agents/samples · 0 tokens

milady-architect

Use for architectural decisions about the elizaOS runtime, plugin resolution, NODEPATH setup, Electrobun boundaries, or cross-layer feature design in the Milady codebase. Invoke before large refactors or any change touching runtime/plugin/desktop seams. Pairs with milady-feature-coordinator for execution.

milady-ai/milady · 66 tokens

04-worker-mode

Worker mode allows an agent to dispatch complex, long-running tasks to background "copy" agents while the main agent stays fully interactive. When a worker finishes, its result is automatically surfaced back to the user through the main agent's conversation.

SmythOS/sre · 0 tokens

03-planner-mode

Planner mode gives an agent systematic planning capabilities. When the agent receives a complex or multi-step task, it will create a structured plan, track each step's progress, and verify completion before finishing.

SmythOS/sre · 0 tokens

00-creating-agents

The SmythOS SDK offers flexible ways to create and configure agents. This guide covers everything from basic agent creation to advanced model configuration.

SmythOS/sre · 0 tokens

01-skills

Skills are the building blocks that give agents their capabilities. Each skill is a function that the agent's LLM can decide to call based on the user's prompt.

SmythOS/sre · 0 tokens