Borrowing it
Nothing to install: this file belongs to jonathan-vella/apex-accelerator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jonathan-vella/apex-accelerator/main/.github/instructions/no-interactive-shell.instructions.mdgit clone --depth 1 https://github.com/jonathan-vella/apex-acceleratorWrote 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/jonathan-vella/apex-accelerator/no-interactive-shell)<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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 5.1 | $0.01485 | $0.01485 |
| Opus 5.5 | $0.00594 | $0.00594 |
| Sonnet 5.5 | $0.00297 | $0.00297 |
| Haiku 4.5 | $0.00148 | $0.00148 |
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 6d 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 — 120 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,confirmdialogs) and long-output terminal replays bloat the chat transcript and re-inject 50+ lines into every subsequent turn.
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 |
Verify authorized targets; use a noninteractive move |
rm -i path |
Verify the exact authorized path, or leave deletion to the user |
cp -i src dst |
Verify overwrite authorization before a noninteractive copy |
read -p "Continue? " ans |
Use ask_user to gather input |
bash -c 'rm -i x' |
Verify authorization; do not hide a prompt in a shell wrapper |
If the user genuinely needs confirmation, use the ask_user
tool — never an interactive shell prompt.
Sub-rule 1a — Aliased rm/mv/cp are still interactive
A plain command can still prompt through a shell alias. Bypass aliases with
command only after verifying the operation, exact targets and any overwrite/deletion
authorization. Noninteractive flags do not grant permission.
If a command becomes silent, inspect its actual output and status; silence or elapsed
time alone never authorizes confirmation. Respond only to a visible, expected prompt
for the already authorized operation and targets. Otherwise stop and return the blocker
to the interactive parent; do not blindly send input or retry with force flags.
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
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.
- 6d ago Changed · +27 lines · +321 tokens per session a16bd108655d
- 1mo ago Changed · -31 lines · -272 tokens per session ef7e5d77cfda
- 1mo ago Changed · +3 lines · +40 tokens per session 573fea8fe487
- 1mo ago First seen · 121 lines · 1,396 tokens per session scan A 41c2163200a2
apex-accelerator no-interactive-shell.instructions.md is an instructions file published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed yesterday), licensed MIT. It adds 1,485 tokens to every session, about $0.0059 per session on Opus 5.5. 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.
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).
next.js AGENTS.md
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, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.