Rules

Auto-discovered instruction files for agent behavior

The rules command manages auto-discovered instruction files that control agent behavior.

Quick Start

# List all loaded rules
praisonai rules list

CLI Auto-Injection

praisonai run, praisonai chat, and bare prompts (praisonai "…", which route to run) automatically load project instruction files from the current directory (and walk up to the git root). Zero config required — drop an AGENTS.md into your project and every modern-engine invocation sees it.

Opt-out

Precedence

1. --no-rules (always wins)
2. --include-rules <names> (manual list or auto)
3. [rules] auto in config.toml
4. Default: auto-loading on

Size caps

Files over the per-file cap are truncated with a warning. Total context stops at max_chars.

Verbose output

praisonai run "Refactor the auth module" --verbose
# Loaded project instructions: AGENTS.md, CLAUDE.md

Only root-priority files (AGENTS.md, CLAUDE.md, PRAISON.md, GEMINI.md, .cursorrules, .windsurfrules) are listed — modular rules under .praison/rules/ and globals are loaded silently.

Usage

!Manage Auto-Discovered Rules

List Rules

praisonai rules list

Native standalone output — one line per rule (<name> [<activation>] - <description-truncated-to-60-chars>):

PRAISON.md [always] - PraisonAI native project instructions
CLAUDE.md [always] - Claude Code memory file
python-guidelines [glob] - Use type hints and follow PEP 8 across all Pyth…

When the workspace has no rules, it prints:

No rules found. Create PRAISON.md, CLAUDE.md, AGENTS.md, or files in .praison/rules/

Wrapper output — the full wrapper renders a Rich panel instead:

╭─ Loaded Rules ───────────────────────────────────────────────────────────────╮
│  📜 PRAISON.md (project root)                                               │
│  📜 CLAUDE.md (project root)                                                │
│  📜 .cursorrules (project root)                                             │
│  📜 python-guidelines.md (.praison/rules/)                                  │
╰──────────────────────────────────────────────────────────────────────────────╯

Add Rule

Native standalone — both <name> and <content> are required. Creates a workspace-scoped rule under .praison/rules/<name>.md with activation="always":

praisonai rules add my_rule "Always use type hints"

Missing content exits 1:

Rule content required. Usage: praisonai rules add <name> <content>

Clear Rules

Native standalone — clears only workspace-scoped rules (those rules add created). Hand-authored AGENTS.md / CLAUDE.md / PRAISON.md, global rules, git-root rules, and nested subdir rules are left untouched:

praisonai rules clear
# Cleared 3 rule(s).

Show Rule Details (wrapper only)

praisonai rules show <rule_name>

Create Rule (wrapper only)

praisonai rules create my_rule "Always use type hints"

On standalone, use praisonai rules add my_rule "Always use type hints" instead.

Delete Rule (wrapper only)

praisonai rules delete my_rule

Show Statistics (wrapper only)

praisonai rules stats

Include Rules with Prompts

praisonai "Task" --include-rules security,testing
praisonai "Task" --no-rules

Declared instruction sources

This page covers auto-discovery — files found by convention (AGENTS.md, CLAUDE.md, .cursorrules, etc.). To declare extra sources explicitly, use the top-level instructions: config key or the praisonai run --instructions flag.

Declared sources load up front alongside the auto-discovered walk-up, and --no-rules suppresses both. See Instruction Sources.

Auto-Discovered Files

PraisonAI automatically discovers instruction files from your project root and git root:

Rule File Format

Basic Format

# Guidelines

- Use type hints for all functions
- Follow PEP 8 style guide
- Include docstrings for public methods

With YAML Frontmatter

---
description: Python coding guidelines
globs: ["**/*.py"]
activation: always  # always, glob, manual, ai_decision
---

# Guidelines

- Use type hints
- Follow PEP 8

@Import Syntax

Reference other files in your rules:

# CLAUDE.md
See @README for project overview
See @docs/architecture.md for system design
@~/.praisonai/my-preferences.md

How It Works

1. Discovery: Scans project root and git root for rule files
2. Priority: Higher priority rules override lower priority
3. Injection: Rules are injected into agent system prompts
4. Activation: Rules activate based on globs or manual selection

Activation Modes

Programmatic Usage

from praisonaiagents import Agent

# Agent auto-discovers CLAUDE.md, AGENTS.md, GEMINI.md, etc.
agent = Agent(name="Assistant", instructions="You are helpful.")
# Rules are injected into system prompt automatically

Best Practices

Related

• Rules Feature
• Hooks CLI
• Workflow CLI