apex-accelerator no-interactive-shell.instructions.md

apex-accelerator no-interactive-shell.instructions.md is an instructions file for GitHub Copilot from jonathan-vella/apex-accelerator. It costs 1,396 tokens per session, scanned A, original, MIT.

A set of shell-use rules that prevents interactive prompts and the replay of very long terminal output in the chat. Interactive prompts are commands that stop and wait for a response.

In plain words
What is it for?
Use it when running shell commands, especially file-copying, moving, deleting, confirmation, or long-output commands.
Why use it?
It reduces interruptions and keeps terminal output from flooding the conversation.

Instructions file for GitHub Copilot

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/jonathan-vella/apex-accelerator/no-interactive-shell
Clone the repo
git clone --depth 1 https://github.com/jonathan-vella/apex-accelerator

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for apex-accelerator no-interactive-shell.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jonathan-vella/apex-accelerator/no-interactive-shell.svg)](https://agentmods.dev/instructions/jonathan-vella/apex-accelerator/no-interactive-shell)
Your own site
<a href="https://agentmods.dev/instructions/jonathan-vella/apex-accelerator/no-interactive-shell"><img src="https://agentmods.dev/badge/instructions/jonathan-vella/apex-accelerator/no-interactive-shell.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,396 This file is loaded in full into every session.
When invoked 1,396 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.

ModelPer sessionOnce invoked
Fable 5 $0.01396 $0.01396
Opus 5 $0.00698 $0.00698
Sonnet 5 $0.00279 $0.00279
Haiku 4.5 $0.00140 $0.00140

Measured 4d ago against content hash 41c2163200a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

apex-accelerator no-interactive-shell.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 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.

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.

.github/instructions/no-interactive-shell.instructions.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MANDATORY: No Interactive Shell, No Long-Output Replay

[!CAUTION] Interactive shell prompts (mv -i, rm -i, cp -i, read -p, confirm dialogs) and long-output terminal replays bloat the chat transcript and re-inject 50+ lines into every subsequent turn. The primary control is this instruction file; safe-shell.mjs is a documentation aid that catches drift in committed snippets.

Rule 1 — No interactive flags

NEVER use mv -i, rm -i, cp -i, read -p, or any prompt-driven shell builtin (including inside bash -c '...').

Forbidden Use instead
mv -i src dst mv -f src dst
rm -i path rm -f path (or skip — let the user delete)
cp -i src dst cp -f src dst
read -p "Continue? " ans Use vscode_askQuestions to gather input
bash -c 'rm -i x' rm -f x

If the user genuinely needs confirmation, use the vscode_askQuestions tool — never an interactive shell prompt.

Rule 2 — Pipe long output to a file

For commands likely to produce more than ~50 lines of output, redirect to a file and report only the line count:

# Good
my-cmd > /tmp/my-cmd.out 2>&1 && \
  echo "wrote /tmp/my-cmd.out ($(wc -l </tmp/my-cmd.out) lines)"

# Bad
my-cmd            # spews 800 lines into chat → repeated every turn

When the caller needs specific content, read the file with the file tool, or extract the relevant lines (grep, head, tail, awk).

Sub-rule 2a — Azure CLI output budget

az commands return large JSON envelopes by default. Choose one of:

Goal Recipe
Fire-and-check exit code az <command> --output none && echo OK
Extract a single field az <command> --query "<jmespath>" --output tsv
Capture full output for later inspection az <command> > /tmp/<name>.json && wc -l /tmp/<name>.json
Preview deployment changes az deployment ... what-if --result-format ResourceIdOnly

Read the full file on GitHub · 121 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.

  1. 4d ago First seen · 121 lines · 1,396 tokens per session scan A 41c2163200a2

Subscribe to this mod's changes

apex-accelerator no-interactive-shell.instructions.md is an instructions file published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed 2d ago), licensed MIT. It adds 1,396 tokens to every session, about $0.0070 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 2026-08-30.

Related

Other instructions, from other repositories

squad squad-routing-guard.instructions.md

Squad routing guard — explicit routing rules so the Copilot CLI routes tasks to the right Squad agent instead of handling them directly.

bradygaster/squad · 1,073 tokens

vscode-unify-chat-provider AGENTS.md

Instructions for smallmain/vscode-unify-chat-provider, a project described as: Integrate multiple LLM API providers into VS Code's GitHub Copilot Chat using the Language Model API. One-click use of your Claude Code, Gemini CLI, Antigravity, Github Copilot, OpenAI Codex (ChatGPT Plus/Pro), xAI Grok (SuperGrok / X…

smallmain/vscode-unify-chat-provider · 271 tokens

PlatformPlatform AGENTS.md

Instructions for platformplatform/PlatformPlatform, covering behavioral guidelines, build, test, and format, product management tool, auto memory and source of truth.

platformplatform/PlatformPlatform · 805 tokens

copilot-instructions copilot-instructions.md

Instructions for SebastienDegodez/copilot-instructions, covering copilot instructions, language policy, development code generation and workflow implementation.

SebastienDegodez/copilot-instructions · 364 tokens

github-copilot-rules testing-xunit.instructions.md

This file provides guidelines for writing effective, maintainable tests using xUnit and related tools.

NikiforovAll/github-copilot-rules · 2,276 tokens

github-copilot-rules coding-guidelines.instructions.md

This file provides guidelines for writing clean, maintainable, and idiomatic C# code with a focus on functional patterns and proper abstraction.

NikiforovAll/github-copilot-rules · 716 tokens