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/russodope/ai-cli-kit/claude-mdgit clone --depth 1 https://github.com/russodope/ai-cli-kitWrote 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/russodope/ai-cli-kit/claude-md)<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>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 | $0.00819 | $0.00819 |
| Opus 5 | $0.00409 | $0.00409 |
| Sonnet 5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade C, and why
ai-cli-kit CLAUDE.md scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "${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`) 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:
- Detect the environment — OS, shell type, Python env, Docker/container, SSH context
- Apply correct syntax — quoting, variables, operators, path separators differ per shell
- Add error handling —
set -euo pipefail(bash) or$ErrorActionPreference = 'Stop'(PS) - Use non-interactive flags —
-y,--yes,-f,--non-interactivein all automated commands - Never assume PATH is correct — probe with
command -vor 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
sudoin containers — already root;sudomay 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
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.
- 3d ago First seen · 88 lines · 819 tokens per session scan C 58627809479b
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.
Other instructions, from other repositories
openscreen AGENTS.md
Instructions for getopenscreen/openscreen, covering agents.md, setup commands, development principles, project layout and code style.
stewie-pixel guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
moonproxy-desktop AGENTS.md
Instructions for MoonProxyHQ/moonproxy-desktop, covering moonproxy, 功能, 技术栈, 目录结构 and 配置与数据存储.
claude-code-profiles CLAUDE.md
Instructions for quinnjr/claude-code-profiles, covering claude.md, project, architecture, command interface and directory-local profiles.
sandy CLAUDE.md
Instructions for jamestelfer/sandy, covering claude.md, voice, what is sandy, project layout and dev commands.
bitbottle AGENTS.md
Instructions for proggarapsody/bitbottle, covering agents.md, reference implementations, design principles, automation and workflow.