Agent skill

Readonly Shell

by AdamKyle in AdamKyle/flare

Allows Claude to inspect files with safe read-only shell commands without asking for permission.

MITAuto-check passedDevelopment

Install Readonly Shell

skills CLI
$ npx skills add AdamKyle/flare --skill readonly-shell -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install AdamKyle/flare readonly-shell --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/AdamKyle/flare.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/readonly-shell .claude/skills/readonly-shell && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
readonly-shell
GitHub stars
162
Token cost
~274 tokens
SKILL.md length
122 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Allows Claude to inspect files with safe read-only shell commands without asking for permission.

  • Development work in your project
  • Calls git

What it does

Readonly Shell is an agent skill from AdamKyle/flare. Allows Claude to inspect files with safe read-only shell commands without asking for permission.

Its SKILL.md is about 270 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development. It works with Git. The repository describes itself as: A Simple Browser Based Game. The licence is MIT.

When your agent uses it

  • Development work in your project

Example prompts

  • “Use the readonly-shell skill to allow Claude to inspect files with safe read-only shell commands without asking for permission”
  • “/readonly-shell”

Requirements

  • Docker

What it can do on your machine

Read from SKILL.md and the folder at commit e22bc47. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Readonly Shell loads about 274 tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 122 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~28
When it runs · the whole SKILL.md, loaded when a task matches
~274

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from AdamKyle/flare at commit e22bc47, republished under its MIT licence (© AdamKyle). 122 words, ~274 tokens.

Download SKILL.mdSave it as .claude/skills/readonly-shell/SKILL.md (or your agent's skills folder).
name
readonly-shell
description
Allows Claude to inspect files with safe read-only shell commands without asking for permission.

Read-Only Shell Permissions

Claude may run read-only inspection commands without asking for permission.

Allowed commands:

  • sed
  • grep
  • rg
  • cat
  • find
  • ls
  • pwd
  • head
  • tail
  • wc
  • stat
  • git status
  • git diff
  • git grep

These commands may only inspect files, directories, or git state.

Claude must not run commands that:

  • execute tests
  • execute application code
  • modify files
  • delete files
  • move files
  • install dependencies
  • run migrations
  • touch the database
  • start services
  • profile code

Forbidden unless explicitly approved:

  • phpunit
  • artisan
  • composer
  • npm
  • yarn
  • pnpm
  • mysql
  • psql
  • docker
  • rm
  • mv
  • cp
  • chmod
  • chown
  • touch
  • truncate
  • shell redirects such as >
  • shell redirects such as >>
  • pipes that write files
  • tee

Claude may edit files only when the task explicitly requires code changes and only after inspecting the relevant files.

© AdamKyle, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/readonly-shell of AdamKyle/flare.

Open the folder on GitHubat commit e22bc47

Compare with similar skills

Readonly Shell next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Readonly Shell compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Readonly Shell this skillAdamKyle/flare162—~274Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT
Codebase Knowledge Graph Q&AEgonex-AI/Understand-Anything85k1 repos~1.2kAutomated safety check: PassMIT
Code Design Rationale Investigatorcursor/plugins10k9 repos~2.6kAutomated safety check: PassNone
Understand Diff AnalysisEgonex-AI/Understand-Anything85k1 repos~1.4kAutomated safety check: PassMIT

Similar skills

  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Codebase Knowledge Graph Q&A

    Egonex-AI/Understand-Anything

    Answers questions about a codebase by searching a prebuilt knowledge graph of its files, functions, classes and dependencies, not by rereading every source file.

    85k GitHub starsUsed in 1 repo~1.2k tokens
    DevelopmentAuto-check passed
  • Official

    Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs.

    10k GitHub starsUsed in 9 repos~2.6k tokens
    DevelopmentAuto-check passed
  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    85k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed
  • Understand Explain

    Egonex-AI/Understand-Anything

    Gives an in-depth explanation of one file, function or module by reading the project's knowledge graph and checking that the graph is still fresh.

    85k GitHub starsUsed in 1 repo~1.3k tokens
    DevelopmentAuto-check passed

More from AdamKyle/flare

  • Phpunit Testing

    AdamKyle/flare

    A skill your agent uses when writing, reviewing, or refactoring PHPUnit tests in this repository.

    162 GitHub stars~656 tokensUpdated 2 days ago
    Auto-check passed
  • Back End Conventions

    AdamKyle/flare

    A skill your agent uses when writing, reviewing, or refactoring PHP/Laravel app code in this repository.

    162 GitHub stars~5.6k tokensUpdated 2 days ago
    Auto-check passed

Works with

Categories

Questions about Readonly Shell

What does Readonly Shell do?

Allows Claude to inspect files with safe read-only shell commands without asking for permission. Readonly Shell is an agent skill from AdamKyle/flare. Allows Claude to inspect files with safe read-only shell commands without asking for permission.

When should I use Readonly Shell?

Readonly Shell fits situations like: development work in your project.

How do I install Readonly Shell in Claude Code?

Run `npx skills add AdamKyle/flare --skill readonly-shell -a claude-code`. Or copy the skill folder (.claude/skills/readonly-shell in AdamKyle/flare) into .claude/skills/readonly-shell in your project. Claude Code loads it when a task matches its description.

How do I install Readonly Shell in Codex?

Run `npx skills add AdamKyle/flare --skill readonly-shell -a codex`. Or copy the skill folder (.claude/skills/readonly-shell in AdamKyle/flare) into .agents/skills/readonly-shell in your project. Codex loads it when a task matches its description.

Can I use Readonly Shell in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AdamKyle/flare --skill readonly-shell -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/readonly-shell, .gemini/skills/readonly-shell, .github/skills/readonly-shell and .opencode/skills/readonly-shell in your project.

What does Readonly Shell need to run?

Going by SKILL.md and its folder, Readonly Shell needs the command-line tools its instructions call (git). Our summary lists: Docker.

Does Readonly Shell access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Readonly Shell safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Readonly Shell use?

Readonly Shell is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Readonly Shell use?

About 274 tokens (SKILL.md is roughly 1.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Readonly Shell?

Skills that share tags, products or a category with Readonly Shell: Finishing a Development Branch (obra/superpowers, 296k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Codebase Knowledge Graph Q&A (Egonex-AI/Understand-Anything, 85k stars) and Code Design Rationale Investigator (cursor/plugins, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Readonly Shell?

AdamKyle (a GitHub user) maintains it in AdamKyle/flare, which has 162 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 5, 2026.

Source: AdamKyle/flare on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.