writing-shell

writing-shell is a skill for Claude Code, Codex from alexei-led/cc-thingz. It costs 132 tokens per session (907 once invoked), scanned C, original, MIT.

Guidance for writing shell scripts and command-line automation in languages such as POSIX sh, Bash, Zsh, and Fish.

In plain words
What is it for?
Use it for shell files, hooks, continuous-integration commands, command pipelines, and small scripts that connect command-line tools.
Why use it?
It reduces common scripting problems involving quoting, unsafe file handling, portability, processes, and command pipelines.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for shell files, hooks, continuous-integration commands, command pipelines, and small…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alexei-led/cc-thingz/writing-shell
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.

Any agent
npx skills add alexei-led/cc-thingz --skill writing-shell
Clone the repo
git clone --depth 1 https://github.com/alexei-led/cc-thingz

Made for: Claude Code, Codex.

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 writing-shell

README.md
[![agentmods](https://agentmods.dev/badge/skills/alexei-led/cc-thingz/writing-shell.svg)](https://agentmods.dev/skills/alexei-led/cc-thingz/writing-shell)
Your own site
<a href="https://agentmods.dev/skills/alexei-led/cc-thingz/writing-shell"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/writing-shell.svg" alt="Measured on agentmods" height="20"></a>
Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 907 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00132 $0.00907
Opus 5 $0.00066 $0.00453
Sonnet 5 $0.00026 $0.00181
Haiku 4.5 $0.00013 $0.00091

Measured 7d ago against content hash 3bd1a8d55195, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

writing-shell 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 7d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- Avoid `eval`, `curl | sh`, parsing `ls`, unguarded globbing, and unsafe `rm`/`mv`/`cp` paths.

Makes network callslowCapability

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

- Avoid `eval`, `curl | sh`, parsing `ls`, unguarded globbing, and unsafe `rm`/`mv`/`cp` paths.
src/skills/writing-shell/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shell Development

Scope

  • Use for shell scripts, hooks, CI shell blocks, command pipelines, and local automation glue.
  • In GitHub Actions, own the shell code inside run: blocks. Use operating-infra for workflow YAML structure, jobs, permissions, runners, actions, secrets, caching, concurrency, and policy. Mixed changes compose both skills.
  • Do not use for cloud, Kubernetes, Terraform, host, or network operations; use operating-infra.
  • Do not use for application logic that belongs in Python, Rust, Go, TypeScript, or another project language.

Read references

  • Read patterns.md before non-trivial scripts or pipelines.
  • Read tools.md when choosing external CLI tools or parsing structured data.
  • Read testing.md before adding or changing shell tests or quality gates.

Defaults

  • Follow the existing shebang, shell, style, and project tooling first.
  • For new portable scripts, use POSIX sh when the logic is simple; use Bash when arrays, pipefail, regex, or richer functions are needed.
  • Use Zsh or Fish only for existing files or explicit user intent. Keep Fish/Zsh config separate from portable scripts.
  • Do not rely on the agent's current shell. Put the intended shell in the shebang or invoke it explicitly in tests.
  • Prefer small shell scripts that call stable tools. Move complex data modeling or business logic to a real language.

Core rules

  • Quote expansions unless word splitting is intentional and documented by structure.
  • Avoid eval, curl | sh, parsing ls, unguarded globbing, and unsafe rm/mv/cp paths.
  • Use arrays for arguments in Bash; use newline/NUL-safe loops for filenames.
  • Use mktemp plus cleanup traps for temporary files and directories.
  • Check required external commands when a script depends on them. Do not install tools silently.
  • Account for macOS/BSD versus GNU flag differences when writing portable scripts.
  • Prefer machine-readable output from tools, then parse it with structured parsers.
  • Use looking-up-docs for exact external CLI flags, syntax, or version behavior; do not guess from memory.

Read the full file on GitHub · 77 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 77 lines · 132 tokens per session scan C 3bd1a8d55195

Subscribe to this mod's changes

writing-shell is a skill published in the GitHub repository alexei-led/cc-thingz (35 stars, last pushed 1mo ago), licensed MIT. It adds 132 tokens to every session and 907 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

swiftui-expert

This skill should be used when SwiftUI work requires judgment about Observation and state ownership, view identity or lifecycle, navigation, app-target concurrency, persistence, Apple-platform behavior, accessibility, performance, or architecture. Trigger on "review this SwiftUI screen", "why isn't this view…

johnkozaris/jko-claude-plugins · 133 tokens

dotnet-backend-expert

This skill should be used when the user is writing, reviewing, debugging, or architecting pure .NET backend code for Kestrel-hosted services. It provides expert critique for REST endpoints, SignalR hubs, TypeScript/React client integration shape, pragmatic Rust interop, application services, AppHost-aware project…

mathisk2095/jko-claude-plugins · 181 tokens

esp32-expert

This skill should be used when the user is writing, reviewing, debugging, or architecting C++ firmware for ESP32 and variants (ESP32-S2, S3, C3, C6, H2, P4) using ESP-IDF or PlatformIO. Provides expert critique covering FreeRTOS task design, memory management (IRAM/DRAM/PSRAM), peripheral drivers (I2C/SPI/UART/GPIO)…

mathisk2095/jko-claude-plugins · 193 tokens

python-backend-expert

This skill should be used when the user is writing, reviewing, debugging, or architecting Python backend code using Litestar or FastAPI with SQLAlchemy or Advanced Alchemy. Provides expert critique covering SOLID principles, hexagonal architecture, repository/service patterns, dependency injection, async correctness…

mathisk2095/jko-claude-plugins · 183 tokens

rust-expert

This skill should be used when the user is writing, reviewing, debugging, or architecting Rust code. Detects edition and toolchain from the project. Provides expert critique covering ownership, error handling, unsafe review, async correctness, trait design, type system patterns, performance, SOLID principles, and…

mathisk2095/jko-claude-plugins · 148 tokens

swiftui-expert

This skill should be used when the user is building, reviewing, or debugging SwiftUI views and apps. Detects iOS and Swift version from the project. Covers creating views, state management with @Observable, NavigationStack routing, animations, accessibility, performance optimization, Liquid Glass adoption, design…

mathisk2095/jko-claude-plugins · 162 tokens