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/rjmurillo/ai-agents/powershellgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/powershell)<a href="https://agentmods.dev/instructions/rjmurillo/ai-agents/powershell"><img src="https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/powershell.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 | $0.01225 | $0.01225 |
| Opus 5 | $0.00613 | $0.00613 |
| Sonnet 5 | $0.00245 | $0.00245 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
ai-agents powershell.instructions.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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PowerShell Rules
These rules apply when you write or review PowerShell. Baseline is PowerShell 7+
(cross-platform pwsh), NOT Windows PowerShell 5.1. Write for Linux and macOS
runners as well as Windows. Defer to PSScriptAnalyzer settings in the repo.
Structure
- Make every non-trivial function an advanced function:
[CmdletBinding()]plus aparam()block with typed, attributed parameters ([Parameter(Mandatory)],[ValidateNotNullOrEmpty()],[ValidateSet(...)]). - Use approved verbs (
Get-Verb) andVerb-Nounnames.Get-,Set-,New-,Remove-,Test-. A function namedDoStuffwill not pass review. - Emit objects to the pipeline; let the caller format. Do not
Write-Hostdata. UseWrite-Output(or bare output) for results,Write-Verbose/Write-Warning/Write-Errorfor diagnostics, andWrite-Hostonly for genuine console UX. - Support the pipeline with
process {}blocks andValueFromPipelinewhen a function operates on a stream of inputs.
Cross-Platform
- Build paths with
Join-Pathor[IO.Path]::Combine, never string concatenation with\. Use[IO.Path]::DirectorySeparatorCharwhen you must. - Use
$env:TEMPvia[IO.Path]::GetTempPath()and$HOME, not Windows-only paths. Do not assumeC:\or backslashes. - Prefer
[Environment]::NewLineawareness in tests; normalize line endings when comparing multi-line output across platforms.
Error Handling
- Set
$ErrorActionPreference = 'Stop'at the top of scripts that must fail fast, or pass-ErrorAction Stopper call. Non-terminating errors are silent by default and hide failures. - Wrap risky calls in
try/catch/finally. Catch specific exception types where you can. Clean up infinally. - After calling an external (native) executable, check
$LASTEXITCODEexplicitly and reset it. A non-zero$LASTEXITCODEleft over from one command makes a later step or the whole workflow look failed. - Standardize process exit codes per ADR-035:
0success,1logic or validation error,2usage or configuration error,3external or dependency failure,4authentication or authorization failure (5-99reserved,100+ documented script-specific).exitwith the matching code so callers and CI branch on the cause, not just pass or fail.
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 · 89 lines · 1,225 tokens per session scan A b69ba32fc7d8
ai-agents powershell.instructions.md is an instructions file published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed yesterday), licensed MIT. It adds 1,225 tokens to every session, about $0.0061 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 2026-09-03.
Other instructions, from other repositories
valuecell AGENTS.md
Instructions for ValueCell-ai/valuecell, covering guidelines, python programming, python environment, imports and runtime checks.
ClawAI CLAUDE.md
Claude Code instructions for ihabkhaled/ClawAI, covering clawai — root policy, identity, authority hierarchy (higher wins on conflict), first command, always and work arriving as a document.
agent-compass python.instructions.md
Python conventions that never auto-apply.
rails-instructions rails.instructions.md
Rails Development Rules -- The Rails Way with AI Agents.
openbotx AGENTS.md
Instructions for openbotx/openbotx, covering agents.md, build and run, setup (first time), run backend (dev mode with reload) and run frontend (dev mode, separate terminal).
caddis-plugin fastapi.instructions.md
FastAPI development standards for backend services.