_AGENT_BEST_PRACTICES

_AGENT_BEST_PRACTICES is an agent for Claude Code from davidmatousek/tachi. It costs 0 tokens per session (7,408 once invoked), scanned A, original, Apache-2.0.

A set of guidelines for designing and maintaining agents in the Agentic Oriented Development Kit, a toolkit for building coding agents.

In plain words
What is it for?
Use it when creating, customizing, or reviewing agents and their configuration files.
Why use it?
It gives agent authors a shared structure and checklist instead of leaving decisions about length, metadata, and reliability undocumented.

Agent for Claude Code

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/davidmatousek/tachi/_agent_best_practices
Clone the repo
git clone --depth 1 https://github.com/davidmatousek/tachi

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for _AGENT_BEST_PRACTICES

README.md
[![agentmods](https://agentmods.dev/badge/agents/davidmatousek/tachi/_agent_best_practices.svg)](https://agentmods.dev/agents/davidmatousek/tachi/_agent_best_practices)
Your own site
<a href="https://agentmods.dev/agents/davidmatousek/tachi/_agent_best_practices"><img src="https://agentmods.dev/badge/agents/davidmatousek/tachi/_agent_best_practices.svg" alt="Measured on agentmods" height="20"></a>
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 7,408 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 $0.07408
Opus 5 $0.00000 $0.03704
Sonnet 5 $0.00000 $0.01482
Haiku 4.5 $0.00000 $0.00741

Measured 4d ago against content hash 2096d5c5dbb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

_AGENT_BEST_PRACTICES 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 4d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/_AGENT_BEST_PRACTICES.md · 1,003 lines

How it starts

The opening of the file, as written. The whole thing — 1,003 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Best Practices

This document provides comprehensive guidance for designing, customizing, and maintaining agents in Agentic Oriented Development Kit.


Table of Contents

  1. Core Principles
  2. Standard Agent Structure
  3. Metadata Specification
  4. Quality Checklist
  5. Preservation-First Enhancement
  6. Template Variables
  7. Common Patterns
  8. Examples

1. Core Principles

All agents in Agentic Oriented Development Kit follow eleven core principles. Principles 1-8 are foundational. Principles 9-11 are inspired by the 12-Factor Agents methodology and target production resilience.

Principle 1: Conciseness

Target: 150-250 lines optimal, 300 lines maximum (with documented justification)

Why: Large agent files cause slow context loading and high token consumption. Concise agents load faster and respond more quickly.

How to achieve:

  • Remove redundant explanations
  • Replace verbose paragraphs with bullet points
  • Move code examples to skill references
  • Eliminate obvious or self-explanatory content

Example:

# Bad (verbose)
When you need to review the architecture of a system, you should first
carefully examine all the components and understand how they interact
with each other. This involves looking at the database layer, the API
layer, the frontend components, and any external services.

# Good (concise)
Architecture review steps:
- Examine component interactions (database, API, frontend, external services)
- Identify integration points
- Validate against system requirements

Principle 2: Structure

Target: All agents use identical 8-section format

Why: Consistent structure enables predictable navigation, easier customization, and automated validation. Template adopters know exactly where to find information.

Read the full file on GitHub · 1,003 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. 4d ago First seen · 1,003 lines · 0 tokens per session scan A 2096d5c5dbb2

Subscribe to this mod's changes

_AGENT_BEST_PRACTICES is an agent published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 22d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 7,408 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.

Related

Other agents, from other repositories