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 skills add alexei-led/cc-thingz --skill writing-shellgit clone --depth 1 https://github.com/alexei-led/cc-thingzWrote 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/skills/alexei-led/cc-thingz/writing-shell)<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>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 | $0.00132 | $0.00907 |
| Opus 5 | $0.00066 | $0.00453 |
| Sonnet 5 | $0.00026 | $0.00181 |
| Haiku 4.5 | $0.00013 | $0.00091 |
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. 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. Useoperating-infrafor 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
shwhen 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, parsingls, unguarded globbing, and unsaferm/mv/cppaths. - Use arrays for arguments in Bash; use newline/NUL-safe loops for filenames.
- Use
mktempplus 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-docsfor exact external CLI flags, syntax, or version behavior; do not guess from memory.
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.
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.
- 7d ago First seen · 77 lines · 132 tokens per session scan C 3bd1a8d55195
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.
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…
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…
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)…
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…
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…
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…