programming-shell

programming-shell is a skill for Claude Code from wahidyankf/ose-public. It costs 47 tokens per session (927 once invoked), scanned A, original, MIT.

A shell scripting guide for applying the project's shell rules while changing scripts. It checks the declared shell dialect, decides whether a task belongs in shell, and tests scripts as their callers use them.

In plain words
What is it for?
Use it when writing or changing shell scripts that run commands, pass files, or stop on failure. It helps check syntax, analysis, formatting, and script tests.
Why use it?
It helps prevent scripts from relying on the wrong shell behaviour or assuming that error handling covers every command. It also flags complex logic that is likely to be unsafe or hard to maintain in shell.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it when writing or changing shell scripts that run commands, pass files, or stop on failure. It helps check syntax, analysis, formatting, and script tests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wahidyankf/ose-public/programming-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 wahidyankf/ose-public --skill programming-shell
Clone the repo
git clone --depth 1 https://github.com/wahidyankf/ose-public

Made for: Claude Code.

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 programming-shell

README.md
[![agentmods](https://agentmods.dev/badge/skills/wahidyankf/ose-public/programming-shell/github.svg)](https://agentmods.dev/skills/wahidyankf/ose-public/programming-shell)
Your own site
<a href="https://agentmods.dev/skills/wahidyankf/ose-public/programming-shell"><img src="https://agentmods.dev/badge/skills/wahidyankf/ose-public/programming-shell/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for programming-shell

Your own site · 80×15
<a href="https://agentmods.dev/skills/wahidyankf/ose-public/programming-shell"><img src="https://agentmods.dev/badge/skills/wahidyankf/ose-public/programming-shell.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 927 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00047 $0.00927
Opus 5.5 $0.00019 $0.00371
Sonnet 5.5 $0.00009 $0.00185
Haiku 4.5 $0.00005 $0.00093

Measured 2d ago against content hash 73313c9a2a98, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

programming-shell scanned grade A with 0 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 2d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/programming-shell/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shell Programming

Shell Scripts owns script mechanics, and Shell Standards owns every shell stack rule. Test-Driven Development and Test Boundaries and Gates govern tests and gates, Red, Green, Refactor runs each cycle, and Developing Applications carries the judgement that holds in every language. This skill adds only the procedure and judgement of applying them in shell. Where a sentence here seems to state a rule, the standards decide.

Start From the First Line

Read the interpreter line and the strict-mode setting before anything else; they decide which dialect's rules apply. Run the analyser, the formatter check, and the script's tests on the untouched tree. A gate already failing is handled under Preexisting Error Resolution. For a dialect the analyser cannot read, the syntax check passes and you carry the review the analyser would have done.

Decide Whether It Belongs in Shell

Before adding logic, ask what the addition is. Running commands in order, passing files between them, and stopping on failure is shell's job. Parsing a structured format beyond a single jq query, computing over data, retrying with backoff, or branching on many cases is logic; once a change adds some, the standard's size rule decides whether the script moves to a language with a unit layer. Raise it before writing the logic, not after.

Trace Where Exit-on-Error Does Not Reach

Strict mode stops the script at a failing command only where the shell checks it. Read each change for the places the standard lists: a function called as a condition, a command on the left of && or ||, a declaration assigned from a substitution, and a substitution in a shell that does not inherit the setting. At each one, ask what happens when the command fails. If the answer is that the script carries on, check the status explicitly.

Read the full file on GitHub · 66 lines

Files

What ships with it

1 file 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. 2d ago First seen · 66 lines · 47 tokens per session scan A 73313c9a2a98

Subscribe to this mod's changes

programming-shell is a skill published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 927 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-14.

Related

Other skills, from other repositories

typescript-test-writing

Use this skill when writing or modifying tests in the llxprt-code repository. Covers mandatory TDD, behavioral testing, bun:test conventions and file naming, mock hygiene (no mock theater), and what never to test. Distilled from dev-docs/RULES.md, which remains the source of truth.

vybestack/llxprt-code · 66 tokens

typescript-eval

Test TypeScript code snippets before persisting as skills.

vellum-ai/vellum-assistant · 14 tokens

Unit Test Scaffold (TypeScript)

Generate TypeScript unit test skeletons (Jest/Vitest) from specifications.

s977043/river-review · 23 tokens

typescript-standard

Apply opinionated TypeScript and testing standards — strict mode with no any, 10-20 line methods, and a test-first loop using data builders, Faker, and Given-When-Then. Use when writing, reviewing, or testing TypeScript, setting up Jest or Playwright, or checking TS code against a project's conventions.

didacrios/ai-coding-protocols · 71 tokens

quality-gates-node

Quality gates determinísticos para aplicações e serviços Node.js, JavaScript e TypeScript. Use quando o usuário pedir "quality gate Node.js", ESLint ou tsc em Node.js, testes, cobertura, complexidade, SAST, SCA, build ou baseline para Node.js.

pwdev-solucoes/pwdev-claude-marketplace · 62 tokens

ts-quality

A TypeScript quality-checking workflow that runs the TypeScript compiler, ESLint, Prettier, and tests. TypeScript is JavaScript with static type checking; ESLint checks code patterns, and Prettier checks formatting.

morodomi/dev-crew · 53 tokens