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.
npx agentmods add instructions/yz9yt/p0g/agents-mdgit clone --depth 1 https://github.com/yz9yt/P0GWrote 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.
[](https://agentmods.dev/instructions/yz9yt/p0g/agents-md)<a href="https://agentmods.dev/instructions/yz9yt/p0g/agents-md"><img src="https://agentmods.dev/badge/instructions/yz9yt/p0g/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.03409 | $0.03409 |
| Opus 5 | $0.01705 | $0.01705 |
| Sonnet 5 | $0.00682 | $0.00682 |
| Haiku 4.5 | $0.00341 | $0.00341 |
Grade C, and why
P0G AGENTS.md scanned grade C 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 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
test -d target_dir && rm -rf target_dir How it starts
The opening of the file, as written. The whole thing — 511 lines — stays where its author put it; the contents beside it link to each section on GitHub.
P0G Agent Guidelines
This document defines the operational rules, patterns, and accumulated knowledge for all P0G agents.
Table of Contents
- Core Principles
- Directory Structure
- File Operations
- Workflow Execution
- Coding Standards
- Verification Patterns
- State Management
- Communication Protocol
- Error Handling
- Learned Patterns
Core Principles
1. Clean Instance Mindset
Every agent invocation is stateless. Never assume:
- Previous file states
- Cached variables or context
- Prior agent actions completed successfully
Always: Read, verify, then act.
2. Explicit Over Implicit
- Document all decisions
- Log all actions to
progress.txt - Never rely on side effects
3. Minimal Footprint
- Change only what's necessary
- Prefer edits over rewrites
- Avoid creating unnecessary files
4. Verification First
- Every action must be verifiable
- If it can't be verified, it didn't happen
- Trust shell exit codes
Directory Structure
project_root/
├── .agent/
│ ├── workflows/ # Slash commands (/p0g-*)
│ │ ├── p0g-np.md # Phase 1: Discovery
│ │ ├── p0g-plan.md # Phase 2: Architecture
│ │ ├── p0g-tasks.md # Phase 3: Task breakdown
│ │ ├── p0g-loop.md # Phase 4: Execution
│ │ └── p0g-surgeon.md # Reactive: Bug decomposer
│ └── rules/ # Optional: paradigm rules (e.g., functional.md)
├── agents/
│ └── p0g/
│ ├── prompts/ # Agent personalities
│ │ ├── discovery.md
│ │ ├── architect.md
│ │ ├── tasker.md
│ │ ├── executor.md
│ │ └── surgeon.md
│ └── skills/
│ └── SKILL.md # Backup/rollback/recovery
├── .p0g/ # Safety infrastructure
│ ├── backups/ # Full project snapshots
│ ├── snapshots/ # Task-level before/after
│ ├── checkpoints/ # Feature-level milestones
│ └── surgery.json # Active surgical plan (if any)
├── prd.json # Single source of truth
├── progress.txt # Append-only execution log
├── errors.log # Error tracking
└── AGENTS.md # This file: guidelines and patterns
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.
- 4d ago First seen · 511 lines · 3,409 tokens per session scan C 3812952b5cb9
P0G AGENTS.md is an instructions file published in the GitHub repository yz9yt/P0G (11 stars, last pushed 5mo ago), licensed MIT. It adds 3,409 tokens to every session, about $0.0170 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
ai-for-non-developers CLAUDE.md
Claude Code instructions for lufermalgo/ai-for-non-developers, covering ai for non-developers — agent rules, 1. token efficiency — the fundamental principle, 2. communication, 3. state & memory and 4. discovery (sdd).
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
OwnPilot AGENTS.md
Instructions for ownpilot/OwnPilot, covering ownpilot, architecture, key patterns, commands and tech stack.
toh-framework CLAUDE.md
Claude Code instructions for wasintoh/toh-framework, covering claude.md — toh framework (repo development guide), what this is, everyday commands, verification protocol and single source, transformed per ide.
awesome-copilot-id AGENTS.md
AGENTS.md instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
codevira CLAUDE.md
Instructions for sachinshelke/codevira, covering codevira — persistent project memory, when to call which codevira tool, at the start of every session, before modifying any file and before adopting a pattern, library, or naming convention.