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/ksyed0/planvisualizer/agents-mdgit clone --depth 1 https://github.com/ksyed0/PlanVisualizerWhat 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 | $0.08993 | $0.08993 |
| Opus 5 | $0.04496 | $0.04496 |
| Sonnet 5 | $0.01799 | $0.01799 |
| Haiku 4.5 | $0.00899 | $0.00899 |
Grade A, and why
PlanVisualizer AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 731 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — AI Agent Operating Standards
This file defines the operational principles, architecture, and collaboration standards for all AI agents working on this project. It is platform-agnostic and applies equally whether the agent is Claude (Anthropic), Gemini (Google), OpenCode, or any other AI coding assistant. Read this file in full at the start of every session, before any code is written or tools are built.
Platform note: This file is named
AGENTS.mduniversally. The companion project constitution file is namedPROJECT.mdregardless of platform. If your AI tool requires a platform-specific filename (e.g.,gemini.mdfor Antigravity,CLAUDE.mdfor Claude Code), create a symlink or copy pointing toPROJECT.md— do not maintain separate content.
🟢 Protocol 0: Initialization (Mandatory)
Before any code is written or tools are built:
- Verify all project files exist — Create any that are missing. The full file list and purpose of each is defined in the 📂 File & Deliverable Structure table at the end of this document.
- Initialize
PROJECT.md— Ensure the Project Constitution is populated with data schemas, behavioral rules, architectural invariants, user profile (§5), and design system (§6). - Halt Execution — No code or scripts may be written until:
- All Discovery Questions in
PROJECT.mdare answered (see Phase 1) - The Data Schema in
PROJECT.mdis confirmed task_plan.mdhas an approved Blueprint
🏗️ Phase 1: B — Blueprint (Vision & Logic)
Discovery: At project start, ask the user the following 5 questions:
- North Star: What is the singular desired outcome?
- Integrations: Which external services are needed? Are credentials ready?
- Source of Truth: Where does the primary data live?
- Delivery Payload: How and where should the final result be delivered?
- Behavioral Rules: How should the system act? (tone, logic constraints, “Do Not” rules)
Data-First Rule: Define the JSON Data Schema (input/output shapes) before any coding begins. Coding only starts once the payload shape is confirmed.
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.
- 2d ago First seen · 731 lines · 8,993 tokens per session scan A b09e75651b31
PlanVisualizer AGENTS.md is an instructions file published in the GitHub repository ksyed0/PlanVisualizer (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 8,993 tokens to every session, about $0.0450 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.