AGENT

An autonomous AI system that observes a situation, reasons about a goal, and takes actions with tools. Different agents can specialize in tasks such as code review, testing, documentation, or frontend development.

In plain words
What is it for?
Use it to design or understand task-oriented and specialist AI agents for coding, analysis, quality checks, and other defined workflows.
Why use it?
It provides a way to automate repeatable work that otherwise requires a person to inspect information, decide what to do, and carry it out.

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/daffy0208/ai-dev-standards/agent
Clone the repo
git clone --depth 1 https://github.com/daffy0208/ai-dev-standards
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 2,643 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 $0.00000 $0.02643
Opus 5 $0.00000 $0.01321
Sonnet 5 $0.00000 $0.00529
Haiku 4.5 $0.00000 $0.00264

Measured 2d ago against content hash c23c52a346ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AGENT 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/AGENT.md · 433 lines

How it starts

The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What Are Agents?

Definition

An agent is an autonomous AI system that can perceive its environment, make decisions, and take actions to achieve specific goals. In the context of AI development, agents are specialized AI entities that:

  1. Perceive - Understand the current state of a task or problem
  2. Reason - Apply domain knowledge to determine the best approach
  3. Act - Execute tools, make decisions, and produce outputs
  4. Learn - Improve performance based on feedback and results

Types of Agents

1. Task-Oriented Agents

Execute specific, well-defined tasks with clear inputs and outputs.

Examples:

  • Code review agent
  • Test generation agent
  • Documentation writer agent
  • Bug finder agent

When to use:

  • Single-purpose automation
  • Repeatable workflows
  • Quality assurance tasks
  • Code analysis operations

2. Skill-Based Agents

Embody domain expertise and methodologies. Each agent represents a specialized capability.

Examples:

  • mvp-builder - Rapid product development
  • rag-implementer - Retrieval-augmented generation systems
  • frontend-builder - React/Next.js development
  • security-engineer - Security best practices

When to use:

  • Domain-specific development
  • Following established methodologies
  • Applying specialized knowledge
  • Complex multi-step workflows

3. Tool-Powered Agents

Agents that leverage MCP (Model Context Protocol) servers to extend their capabilities.

Examples:

  • Agent with vector database tools (Pinecone, Weaviate)
  • Agent with web scraping tools
  • Agent with code analysis tools
  • Agent with deployment tools

When to use:

  • Need external tool integration
  • API interactions required
  • Database operations
  • File system manipulations

4. Multi-Agent Systems

Coordinated groups of agents working together on complex problems.

Examples:

  • Product team: strategist + designer + builder + tester
  • RAG pipeline: chunker + embedder + retriever + generator
  • CI/CD system: linter + tester + builder + deployer

Read the full file on GitHub · 433 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 · 433 lines · 0 tokens per session scan A c23c52a346ea

Subscribe to this mod's changes

AGENT is an agent published in the GitHub repository daffy0208/ai-dev-standards (36 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,643 tokens. 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.