Borrowing it
Nothing to install: this file belongs to fabioc-aloha/Alex_Skill_Mall. 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/fabioc-aloha/Alex_Skill_Mall/main/.github/instructions/terminal-command-safety.instructions.mdgit clone --depth 1 https://github.com/fabioc-aloha/Alex_Skill_MallWrote 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/fabioc-aloha/alex_skill_mall/terminal-command-safety)<a href="https://agentmods.dev/instructions/fabioc-aloha/alex_skill_mall/terminal-command-safety"><img src="https://agentmods.dev/badge/instructions/fabioc-aloha/alex_skill_mall/terminal-command-safety/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/fabioc-aloha/alex_skill_mall/terminal-command-safety"><img src="https://agentmods.dev/badge/instructions/fabioc-aloha/alex_skill_mall/terminal-command-safety.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 | $0.00985 | $0.00985 |
| Opus 5 | $0.00492 | $0.00492 |
| Sonnet 5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00098 | $0.00098 |
Grade A, and why
Alex_Skill_Mall terminal-command-safety.instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Terminal Command Safety
Always-on rationale: terminal commands fire from any task regardless of file context (build, test, git, deployment, exploration). Safety rules — especially the Backtick Hazard — must apply before every run_in_terminal call. A pattern-scoped glob would silence the protection in the cases most likely to ship destructive failures.
Backtick Hazard (Critical)
Backticks break in ALL shells (bash=command substitution, PowerShell=escape char). NEVER place raw backticks inside double-quoted terminal arguments.
| Content contains | Action |
|---|---|
| Backticks | Always use temp file |
| Multi-line text | Prefer temp file |
| Both quote types | Use temp file |
Dollar signs ($) |
Single-quoted heredoc or temp file |
| Plain text only | Inline is safe |
Rules: gh → --body-file, git commit → -F <file>, any CLI → file-based input over inline.
Temp file location matters: place temp files outside the working tree ($env:TEMP\<slug>.txt on Windows, /tmp/<slug>.txt on Unix) OR add the pattern to .gitignore before staging. Otherwise git add -A will stage and commit the message file itself. S360 hit this twice in 2026-05 (commits 26631b4 then caught mid-flight on the next leak via Tenet X self-review).
Preferred PowerShell template for multi-line commit messages:
$m = Join-Path $env:TEMP "<slug>.txt"
Set-Content -Path $m -Value $msg -NoNewline
git commit -F $m
Remove-Item $m
Filesystem isolation prevents the leak by construction.
Output Capture Failures
Terminal output can be silently lost or truncated.
- Redirect to file, then read:
cmd 2>&1 | Out-File $env:TEMP\out.txt - Pipe pagers through
Out-String - Sentinel:
; echo "EXIT_CODE:$LASTEXITCODE" - Limit volume:
Select-Object -First,-Tail,Format-Table - Avoid alt-buffer programs (
less,vim,man) — use non-interactive equivalents - If empty: retry with
get_terminal_output, then redirect to file, then check stderr
Terminal Hanging
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.
- 9d ago First seen · 71 lines · 985 tokens per session scan A 2f3bcd7f47af
Alex_Skill_Mall terminal-command-safety.instructions.md is an instructions file published in the GitHub repository fabioc-aloha/Alex_Skill_Mall (4 stars, last pushed 2d ago), licensed MIT. It adds 985 tokens to every session, about $0.0049 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.
Other instructions, from other repositories
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.