shell-tools

shell-tools is a skill for Claude Code, Codex from juan294/cc-rpi. It costs 61 tokens per session (1,473 once invoked), scanned A, original, MIT.

A reference guide to shell commands, file tools, and command-line utilities such as zsh, jq, and Python.

In plain words
What is it for?
Use it when writing shell commands, handling JSON output, building regular expressions, invoking linters, or choosing between a built-in tool and a shell command.
Why use it?
It helps avoid mistakes caused by quoting, escaping, changing working directories, and running dependent commands in the wrong order.

Skill for Claude CodeCodex

Part of the cc-rpi plugin — 14 skills, 19 commands, 2 hooks shipped together

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 skills/juan294/cc-rpi/shell-tools
Any agent
npx skills add juan294/cc-rpi --skill shell-tools
Clone the repo
git clone --depth 1 https://github.com/juan294/cc-rpi

Made for: Claude Code, Codex.

Or install cc-rpi, the plugin that ships this one along with the rest of its 14 skills, 19 commands, 2 hooks.

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 shell-tools

README.md
[![agentmods](https://agentmods.dev/badge/skills/juan294/cc-rpi/shell-tools.svg)](https://agentmods.dev/skills/juan294/cc-rpi/shell-tools)
Your own site
<a href="https://agentmods.dev/skills/juan294/cc-rpi/shell-tools"><img src="https://agentmods.dev/badge/skills/juan294/cc-rpi/shell-tools.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,473 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00061 $0.01473
Opus 5 $0.00030 $0.00737
Sonnet 5 $0.00012 $0.00295
Haiku 4.5 $0.00006 $0.00147

Measured 4d ago against content hash 87801b6de7c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shell-tools scanned grade A with 1 finding 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.

Makes network callslowCapability

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

description: "Shell and tool-call environment facts: escaping inside single-quoted zsh/jq/Python strings, complex regex in zsh, absolute paths and cwd resets between Bash calls, linter invocation, curl and JSON output ha
templates/skills/shell-tools/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shell & Tools

Environment facts about the shell, the file tools, and the CLIs around them. These do not become knowable through reasoning -- they are properties of zsh, jq, Python, and the tool layer.

Sequencing Fallible Calls

Wrong -- independent Bash calls issued in parallel; one failure kills all siblings:

# Parallel call 1: pnpm run typecheck
# Parallel call 2: pnpm run lint
# Parallel call 3: pnpm run test

Right -- chain sequentially so each result survives:

pnpm run typecheck 2>&1 ; pnpm run lint 2>&1 ; pnpm run test 2>&1

Use && when a later step is meaningless after an earlier failure, ; when you want every result regardless.

Quoting and Escaping

Inside single quotes, every character is literal. Escaping an operator there inserts a real backslash into the string and breaks the consumer.

Wrong -- backslash reaches jq and Python as data:

jq '.[] | select(.name \!= "review")'   # jq: INVALID_CHARACTER
python3 -c 'assert x \!= y'             # SyntaxError

Right -- write the operator plainly inside '...':

jq '.[] | select(.name != "review")'
python3 -c 'assert x != y'

Complex Regex in zsh

Wrong -- zsh treats !, {, and } specially before the command ever runs:

grep -oP '(?<=version":")[^"]+' package.json
# zsh: event not found

Right -- use the built-in Grep tool, a dedicated linter, or wrap in bash:

bash -c 'grep -oP '"'"'(?<=version":")[^"]+'"'"' package.json'

Reach for the built-in Grep tool first. It takes the pattern as data, so no shell parsing happens at all.

Paths

The file tools do not expand ~, and the shell's working directory resets between Bash calls.

Wrong -- tilde in a file tool, relative path across calls:

Read("~/code/project/src/index.ts")     # no such file
cd ../other-project && pnpm test        # cwd already reset; ../ is wrong

Right -- absolute paths everywhere, and cd inside the same call:

Read("/Users/you/code/project/src/index.ts")

Read the full file on GitHub · 222 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 · 222 lines · 61 tokens per session scan A 87801b6de7c0

Subscribe to this mod's changes

shell-tools is a skill published in the GitHub repository juan294/cc-rpi (5 stars, last pushed 3d ago), licensed MIT. It adds 61 tokens to every session and 1,473 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.