What is GitHub-Template AGENTS.md?

Repository guidance for building and testing a PowerShell module with Sampler, ModuleBuilder, InvokeBuild, Pester, and PSScriptAnalyzer. It also explains the required first-time dependency setup.

Use it to bootstrap dependencies, build the module, run tests and analysis, publish it, or run the local pre-push checks.

It puts the project's build and validation process in one place, so agents do not miss dependency setup or required checks.

GitHub-Template AGENTS.md — Instructions file by christaylorcodes

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 instructions/christaylorcodes/github-template/agents-md

Clone the repo

git clone --depth 1 https://github.com/christaylorcodes/GitHub-Template

Made for: Codex, OpenCode.

Per session 3,803 This file is loaded in full into every session.

When invoked 3,803 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.03803	$0.03803
Opus 5	$0.01902	$0.01902
Sonnet 5	$0.00761	$0.00761
Haiku 4.5	$0.00380	$0.00380

Measured yesterday against content hash db30fbf5f1e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

GitHub-Template 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.

AGENTS.md · 368 lines

How it starts

The opening of the file, as written. The whole thing — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides context for AI coding agents (Claude Code, GitHub Copilot, Cursor, Windsurf, Codex, and others) working in this repository.

Project Overview

ModuleName is a PowerShell module hosted at https://github.com/YOUR-USERNAME/YOUR-REPO.

Language: PowerShell 7.2+
Build System: Sampler / ModuleBuilder
Test Framework: Pester 5.6+
Linter: PSScriptAnalyzer
License: MIT

Quick Start

# Bootstrap dependencies (required first time)
./build.ps1 -ResolveDependency -Tasks noop

# Run full pipeline (Clean -> Build -> Test)
./build.ps1

# Local pre-push validation (build + analyze + test)
./Tests/test-local.ps1

Build Commands

All commands require PowerShell 7.2+ and use Sampler/ModuleBuilder with InvokeBuild as the task runner. Configuration lives in build.yaml and RequiredModules.psd1.

# Individual tasks
./build.ps1 -Tasks test             # Run Pester tests (builds first)
./build.ps1 -Tasks build            # Build module to output/
./build.ps1 -Tasks publish          # Publish to PowerShell Gallery

# Bootstrap + build (first time or after dependency changes)
./build.ps1 -ResolveDependency -Tasks build

# Local validation (build + analyze + test)
./Tests/test-local.ps1
./Tests/test-local.ps1 -SkipBuild       # Skip build step
./Tests/test-local.ps1 -SkipTests       # Skip Pester tests
./Tests/test-local.ps1 -SkipAnalyze     # Skip PSScriptAnalyzer

Architecture

Directory Layout

YOUR-REPO/
  build.ps1                  # Sampler bootstrap and task runner (vendor)
  build.yaml                 # Build pipeline configuration
  RequiredModules.psd1       # Build dependency specifications
  Resolve-Dependency.ps1     # Dependency resolver (vendor)
  Resolve-Dependency.psd1    # Resolver configuration
  source/
    ModuleName.psd1          # Module manifest
    ModuleName.psm1          # Root module (auto-loads subdirectories)
    Classes/                 # PowerShell class definitions (loaded first)
    Private/                 # Internal helper functions (not exported)
    Public/                  # Exported functions (one file per function)
  Tests/
    Unit/Public/             # Tests for exported functions
    Unit/Private/            # Tests for internal functions
    Integration/             # Integration tests
    TestHelpers/             # Shared test utilities
  Templates/                 # Boilerplate for new functions/tests
  Scripts/                   # Automation scripts
  output/                    # Build output (gitignored)
  docs/                      # Documentation and media assets
    media/                   # Logo, demo GIF, donation QR codes

Read the full file on GitHub · 368 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.

yesterday First seen · 368 lines · 3,803 tokens per session scan A db30fbf5f1e2

Subscribe to this mod's changes

GitHub-Template AGENTS.md is an instructions file published in the GitHub repository christaylorcodes/GitHub-Template (2 stars, last pushed 2mo ago), licensed MIT. It adds 3,803 tokens to every session, about $0.0190 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.

Testing

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

GitHub-Template AGENTS.md