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/msitarzewski/phase/agents-mdgit clone --depth 1 https://github.com/msitarzewski/phaseWhat 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 | $0.07953 | $0.07953 |
| Opus 5 | $0.03977 | $0.03977 |
| Sonnet 5 | $0.01591 | $0.01591 |
| Haiku 4.5 | $0.00795 | $0.00795 |
Grade A, and why
phase 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 yesterday.
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.
This is a copy
88% identical to agency-agents-app AGENTS.md — 46 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 982 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Version: 2.1 (2025-10-25) | Compatibility: Claude, Cursor, Copilot, Cline, Aider, all AGENTS.md-compatible tools Status: Canonical single-file guide for AI-assisted development
Table of Contents
- Compliance & Core Rules
- Session Startup
- Memory Bank
- State Machine
- Task Contract & Budgets
- Quality & Documentation
- Example Workflow
- Troubleshooting
1. Compliance & Core Rules
Startup Compliance (Output Every Session)
COMPLIANCE CONFIRMED: Reuse over creation
⚠️ GIGO PREVENTION - User Responsibilities:
📋 Clear task objectives | 🔗 Historical context | 🎯 Success criteria
⚙️ Architectural constraints | 🎖️ You lead - clear input = excellent output
[Continue with Memory Bank loading...]
The Four Sacred Rules
| Rule | Requirement | Validation |
|---|---|---|
| ❌ No new files without reuse analysis | Search codebase, reference files that cannot be extended, provide exhaustive justification | Before creating: "Analyzed X, Y, Z. Cannot extend because [technical reason]" |
| ❌ No rewrites when refactoring possible | Prefer incremental improvements, justify why refactoring won't work | "Refactoring X impossible because [specific limitation]" |
| ❌ No generic advice | Cite file:line, show concrete integration points, include migration strategies |
Every suggestion includes file:line citation |
| ❌ No ignoring existing architecture | Load patterns before changes, extend existing services/components, consolidate duplicates | "Extends existing pattern at file:line" |
Reuse Validation Checklist (Before Creating Files)
- [ ] Searched: [search terms] → found: [list files]
- [ ] Analyzed extension:
- [ ] `existing/file1.ext` - Cannot extend: [specific technical reason]
- [ ] `existing/file2.ext` - Cannot extend: [specific technical reason]
- [ ] Checked patterns: `systemPatterns.md#[section]`
- [ ] Justification: New file needed because [exhaustive reasoning]
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.
- yesterday First seen · 982 lines · 7,953 tokens per session scan A 686f15ac240b
phase AGENTS.md is an instructions file published in the GitHub repository msitarzewski/phase (5 stars, last pushed 22d ago), licensed Apache-2.0. It adds 7,953 tokens to every session, about $0.0398 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to agency-agents-app AGENTS.md, differing in 46 lines, and is treated as a copy.
Other instructions, from other repositories
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.