instructions

A guide to writing system-level instructions that define an agent's role, behavior, abilities, limits, tool use, and response style.

In plain words
What is it for?
Use it to provide default or dynamic instructions, set an agent's tone and responsibilities, and describe how it should handle errors and available tools.
Why use it?
It helps keep agent behavior consistent and makes edge cases and tool usage explicit.

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/activeagents/activeagent/instructions
Clone the repo
git clone --depth 1 https://github.com/activeagents/activeagent
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,519 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00025 $0.02519
Opus 5 $0.00013 $0.01260
Sonnet 5 $0.00005 $0.00504
Haiku 4.5 $0.00003 $0.00252

Measured 2d ago against content hash 51b02e893f96, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

instructions 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.

docs/agents/instructions.md · 367 lines

How it starts

The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{{ $frontmatter.title }}

Instructions are system-level messages that guide how agents behave and respond. They define the agent's personality, capabilities, constraints, and how it should use available tools. Think of instructions as the agent's "operating manual" that shapes every interaction.

Why Instructions Matter

Well-crafted instructions help agents:

  • Understand their role and capabilities
  • Know when and how to use available tools
  • Maintain consistent behavior across interactions
  • Handle edge cases and error scenarios appropriately
  • Provide responses in the desired tone and format

Setting Instructions

ActiveAgent provides five flexible ways to define instructions, from simple strings to dynamic ERB templates.

1. Default Instructions Template

The simplest approach: create an instructions.md (or instructions.text) file in your agent's view directory. ActiveAgent automatically loads it when you call prompt without explicit instructions.

::: code-group <<< @/../test/docs/agents/instructions_examples_test.rb#default_template {ruby:line-numbers} [agent.rb]

<<< @/../test/dummy/app/views/docs/agents/instructions/default_template/agent/instructions.md.erb{erb:line-numbers} [instructions.md] :::

Strict Loading: Pass instructions: true to enforce strict template loading. This will raise an error if the template file cannot be found, useful for catching missing instruction files in production.

# Raises error if instructions.md is missing
generate_with instructions: true

When to use: Most production agents. Keeps instructions organized, version-controlled, and easy to iterate.

2. Inline String Instructions

Pass a string directly to generate_with for simple, static instructions:

<<< @/../test/docs/agents/instructions_examples_test.rb#inline_string {ruby:line-numbers} [agent.rb]

When to use: Quick prototypes, simple agents with minimal instructions, or when instructions fit in one clear sentence.

3. Custom Instructions Template

Read the full file on GitHub · 367 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 · 367 lines · 25 tokens per session scan A 51b02e893f96

Subscribe to this mod's changes

instructions is an agent published in the GitHub repository activeagents/activeagent (971 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 2,519 once invoked, about $0.0001 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 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens