ai-cli-kit CLAUDE.md

ai-cli-kit CLAUDE.md is an instructions file for coding agents from russodope/ai-cli-kit. It costs 819 tokens per session, scanned C, original, MIT.

A set of shell-command rules for an AI coding agent. It requires the agent to identify the operating environment and shell before choosing command syntax and safety settings.

In plain words
What is it for?
Use it to guide environment checks, command construction, error handling, non-interactive execution, and package installation across shells.
Why use it?
It reduces errors caused by wrong shell syntax, missing programs, incorrect paths, or commands that wait for user input.

Instructions file

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/russodope/ai-cli-kit/claude-md
Clone the repo
git clone --depth 1 https://github.com/russodope/ai-cli-kit

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 ai-cli-kit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/russodope/ai-cli-kit/claude-md.svg)](https://agentmods.dev/instructions/russodope/ai-cli-kit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/russodope/ai-cli-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/russodope/ai-cli-kit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 819 This file is loaded in full into every session.
When invoked 819 The same file — it is already loaded in full.
Security scan C 2 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 $0.00819 $0.00819
Opus 5 $0.00409 $0.00409
Sonnet 5 $0.00164 $0.00164
Haiku 4.5 $0.00082 $0.00082

Measured 3d ago against content hash 58627809479b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

ai-cli-kit CLAUDE.md scanned grade C with 2 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 3d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "${DIR:?'DIR not set'}/" # safe delete

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Check network** before any download (`curl -sf URL || exit 1`)
CLAUDE.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Command Rules

Place this file in your project root to apply these rules to Claude Code.

Source: https://github.com/russodope/claude-skill-command-rules

Shell Command Policy

Before writing or executing any shell command:

  1. Detect the environment — OS, shell type, Python env, Docker/container, SSH context
  2. Apply correct syntax — quoting, variables, operators, path separators differ per shell
  3. Add error handlingset -euo pipefail (bash) or $ErrorActionPreference = 'Stop' (PS)
  4. Use non-interactive flags-y, --yes, -f, --non-interactive in all automated commands
  5. Never assume PATH is correct — probe with command -v or use absolute paths

Environment Detection (run first if unsure)

echo "OS: $(uname -s 2>/dev/null || echo Windows)"
echo "Shell: $SHELL"
echo "Python: $(python --version 2>&1 || python3 --version 2>&1)"
[ -f /.dockerenv ] && echo "Inside Docker"
[ -n "$VIRTUAL_ENV" ] && echo "venv: $VIRTUAL_ENV"
[ -n "$CONDA_DEFAULT_ENV" ] && echo "conda: $CONDA_DEFAULT_ENV"

Rules by Shell

bash/zsh:

set -euo pipefail
python3 -m pip install package          # not: pip install
rm -rf "${DIR:?'DIR not set'}/"         # safe delete
./script.sh                             # not: script.sh

PowerShell:

$ErrorActionPreference = 'Stop'
$env:VAR                                # not: %VAR% or $VAR
python -m pip install package
.\.venv\Scripts\Activate.ps1

Docker:

docker run --rm python:3.11-slim cmd    # always --rm, always pin version
docker run --rm -v "$(pwd):/app" img    # bash volume mount

SSH (non-interactive):

ssh -o StrictHostKeyChecking=no -o BatchMode=yes -o ConnectTimeout=10 \
    user@host 'bash -s' << 'EOF'
set -euo pipefail
# remote commands here
EOF

Hard Rules for Claude Code (Agentic Execution)

  • No interactive prompts — every command must run to completion without user input
  • No sudo in containers — already root; sudo may not exist
  • Temp files/tmp/ not current directory
  • Check network before any download (curl -sf URL || exit 1)
  • Probe before use: command -v docker || { echo "docker not found"; exit 1; }
  • Destructive ops → dry-run first, then execute with explicit path

Read the full file on GitHub · 88 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. 3d ago First seen · 88 lines · 819 tokens per session scan C 58627809479b

Subscribe to this mod's changes

ai-cli-kit CLAUDE.md is an instructions file published in the GitHub repository russodope/ai-cli-kit (2 stars, last pushed 6mo ago), licensed MIT. It adds 819 tokens to every session, about $0.0041 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.