Agent skill

Okojo Test262

by akeit0 in akeit0/okojo

Run and continue Okojo Test262 compliance work. An agent skill from akeit0/okojo.

MITAuto-check passedDevelopment

Install Okojo Test262

skills CLI
$ npx skills add akeit0/okojo --skill okojo-test262 -a claude-code

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

GitHub CLI
$ gh skill install akeit0/okojo okojo-test262 --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/akeit0/okojo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/okojo-test262 .claude/skills/okojo-test262 && 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
okojo-test262
GitHub stars
160
Token cost
~742 tokens
SKILL.md length
254 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Run and continue Okojo Test262 compliance work. An agent skill from akeit0/okojo.

  • Works in 7 steps: reproduce the exact Test262 case → classify it as engine/compiler/runtime… → compare V8 for language/compiler/VM… → …
  • Ordinary Okojo implementation
  • SKILL.md covers Core policy, Workflow, Focused engine loop and Test262 runner, plus 1 more section
  • Calls dotnet

What it does

Okojo Test262 is an agent skill from akeit0/okojo. Run and continue Okojo Test262 compliance work. Use only when the request involves Test262, Test262Runner, compliance sweeps, failing Test262 cases, the passed cache, or SkipList. Do not use for ordinary Okojo implementation, refactoring, review, or debugging.

Its SKILL.md is about 740 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, covering Refactoring. It works with C#, JavaScript and .NET. The repository describes itself as: Okojo is an experimental low allocation managed JavaScript engine for .NET. The licence is MIT.

When your agent uses it

  • Ordinary Okojo implementation
  • Tasks that involve Refactoring

Example prompts

  • “/okojo-test262”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. reproduce the exact Test262 case
  2. classify it as engine/compiler/runtime behavior or intentionally unsupported coverage
  3. compare V8 for language/compiler/VM behavior or Node for built-in/runtime behavior
  4. implement the narrow root-cause fix
  5. add a focused regression under tests/Okojo.Tests
  6. rebuild the runner before trusting an exact rerun
  7. rerun the exact case, nearby coverage, and the requested continuation batch

What it can do on your machine

Read from SKILL.md and the folder at commit 478ec2d. 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:

    • dotnet

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

  • Network

    No URLs in SKILL.md.

    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

Okojo Test262 loads about 742 tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 254 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~69
When it runs · the whole SKILL.md, loaded when a task matches
~742

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 akeit0/okojo at commit 478ec2d, republished under its MIT licence (© akeit0). 254 words, ~742 tokens.

Download SKILL.mdSave it as .claude/skills/okojo-test262/SKILL.md (or your agent's skills folder).
name
okojo-test262
description
Run and continue Okojo Test262 compliance work. Use only when the request involves Test262, Test262Runner, compliance sweeps, failing Test262 cases, the passed cache, or SkipList. Do not use for ordinary Okojo implementation, refactoring, review, or debugging.

Okojo Test262

Use this skill only for Test262-driven work in tools/Test262Runner and the engine/test files needed to resolve a selected Test262 failure. Ordinary engine work belongs to the general Okojo development workflow.

Core policy

Fix standards-aligned behavior.

Do not prioritize deprecated/legacy behavior unless explicitly re-approved. Treat these as intentionally unsupported by default:

  • direct-eval-specific semantics
  • with
  • legacy __proto__
  • deprecated legacy accessor APIs
  • Function.prototype.arguments / Function.prototype.caller
  • arguments.callee

For these, prefer narrow intended Test262 skips with a clear reason over regressing core paths.

Do not add a skip merely to make a run green. A skip requires an intentionally unsupported feature or an explicit user decision.

Workflow

  1. reproduce the exact Test262 case
  2. classify it as engine/compiler/runtime behavior or intentionally unsupported coverage
  3. compare V8 for language/compiler/VM behavior or Node for built-in/runtime behavior
  4. implement the narrow root-cause fix
  5. add a focused regression under tests/Okojo.Tests
  6. rebuild the runner before trusting an exact rerun
  7. rerun the exact case, nearby coverage, and the requested continuation batch

Focused engine loop

powershell
dotnet build tests/Okojo.Tests/Okojo.Tests.csproj -c Release /p:UseSharedCompilation=false
dotnet test tests/Okojo.Tests/Okojo.Tests.csproj -c Release --no-build --filter <Name>

When the runner is involved:

powershell
dotnet build tools/Test262Runner/Test262Runner.csproj -c Release /p:UseSharedCompilation=false

Test262 runner

Show help:

powershell
dotnet run --project tools/Test262Runner/Test262Runner.csproj -c Release -- --help

Common continuation pattern:

powershell
dotnet run --project tools/Test262Runner/Test262Runner.csproj -c Release -- --max-tests 30 --full-path --skip-passed

Array.prototype sweep example:

powershell
dotnet run --project tools/Test262Runner/Test262Runner.csproj -c Release -- --max-tests 30 --category built-ins --filter Array/prototype --full-path --skip-passed

Useful runner notes:

  • --skip-passed uses the local passed cache
  • rebuild the runner after runtime/compiler changes before trusting exact reruns
  • SkipList.cs contains intentional exclusions
  • do not run a broad sweep when an exact or category-filtered rerun answers the current question

Editing guidance

  • Prefer minimal, local fixes.
  • Add a focused regression test for each fix.
  • Do not revert unrelated user changes.
  • Do not widen policy support accidentally just to satisfy a single Test262 file.

© akeit0, 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 .agents/skills/okojo-test262 of akeit0/okojo.

Open the folder on GitHubat commit 478ec2d

Compare with similar skills

Okojo Test262 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.

Okojo Test262 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Okojo Test262 this skillakeit0/okojo160—~742Automated safety check: PassMIT
Add Refactoringdotnet/roslynator3.5k—~946Automated safety check: PassCustom licence
Dynamo Dotnet ExpertDynamoDS/Dynamo2k—~922Automated safety check: PassApache-2.0
Deprecate Analyzer Or Refactoringdotnet/roslynator3.5k—~511Automated safety check: PassCustom licence
Dotnet10 Featuresrunceel/ReactiveProperty944—~2.7kAutomated safety check: PassMIT
Git HooksProrise-cool/Claude-Code-Multi-Agent305—~3.6kAutomated safety check: NotesNone

Similar skills

  • Add Refactoring

    dotnet/roslynator

    Official

    A skill your agent uses when adding a new RR refactoring in roslynator, editing Refactorings.xml, registering in RefactoringContext, or when refactorings-testing.md shows XunitRefactoringVerifier —…

    3.5k GitHub stars~946 tokensUpdated 4 days ago
    DevelopmentAuto-check passed
  • Dynamo Dotnet Expert

    DynamoDS/Dynamo

    Write and review C/.NET code in Dynamo following Dynamo coding standards, modern C patterns, and repo conventions.

    2k GitHub stars~922 tokensUpdated today
    DevelopmentAuto-check passed
  • Official

    A skill your agent uses when obsoleting or retiring RCS, RR, or RCF in roslynator, replacing an analyzer with another id, or when tempted to use IsObsolete on an Analyzer entry — analyzers use…

    3.5k GitHub stars~511 tokensUpdated 4 days ago
    DevelopmentAuto-check passed
  • Dotnet10 Features

    runceel/ReactiveProperty

    Reference for the .NET 10 / C 14 features that are relevant to the ReactiveProperty repository.

    944 GitHub stars~2.7k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Git Hooks

    Prorise-cool/Claude-Code-Multi-Agent

    Central authority on git hook implementations, modern best practices, and tooling for .NET/C, JavaScript/TypeScript, Python, and polyglot repositories.

    305 GitHub stars~3.6k tokensUpdated 22 days ago
    DevelopmentAuto-check: notes
  • Refactor Analysis

    Samsung/TizenFX

    Automatically scans the TizenFX codebase on a rotating schedule to discover .NET 8 / C 12+ refactoring targets and register them as GitHub Issues.

    214 GitHub stars~2.6k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from akeit0/okojo

  • Debug Okojo.Node large-app failures through sandbox/OkojoInkProbe and sandbox/OkojoNodeDebugSandbox.

    160 GitHub stars~798 tokensUpdated 17 days ago
    Auto-check passed
  • Develop or debug Okojo ECMAScript engine internals. An agent skill from akeit0/okojo.

    160 GitHub stars~509 tokensUpdated 17 days ago
    Auto-check passed

Categories

Questions about Okojo Test262

What does Okojo Test262 do?

Run and continue Okojo Test262 compliance work. An agent skill from akeit0/okojo. Okojo Test262 is an agent skill from akeit0/okojo. Run and continue Okojo Test262 compliance work.

When should I use Okojo Test262?

Okojo Test262 fits situations like: ordinary Okojo implementation; tasks that involve Refactoring.

How do I install Okojo Test262 in Claude Code?

Run `npx skills add akeit0/okojo --skill okojo-test262 -a claude-code`. Or copy the skill folder (.agents/skills/okojo-test262 in akeit0/okojo) into .claude/skills/okojo-test262 in your project. Claude Code loads it when a task matches its description.

How do I install Okojo Test262 in Codex?

Run `npx skills add akeit0/okojo --skill okojo-test262 -a codex`. Or copy the skill folder (.agents/skills/okojo-test262 in akeit0/okojo) into .agents/skills/okojo-test262 in your project. Codex loads it when a task matches its description.

Can I use Okojo Test262 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 akeit0/okojo --skill okojo-test262 -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/okojo-test262, .gemini/skills/okojo-test262, .github/skills/okojo-test262 and .opencode/skills/okojo-test262 in your project.

What does Okojo Test262 need to run?

Going by SKILL.md and its folder, Okojo Test262 needs the command-line tools its instructions call (dotnet).

Does Okojo Test262 access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Okojo Test262 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 Okojo Test262 use?

Okojo Test262 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 Okojo Test262 use?

About 742 tokens (SKILL.md is roughly 3k 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 Okojo Test262?

Skills that share tags, products or a category with Okojo Test262: Add Refactoring (dotnet/roslynator, 3.5k stars), Dynamo Dotnet Expert (DynamoDS/Dynamo, 2k stars), Deprecate Analyzer Or Refactoring (dotnet/roslynator, 3.5k stars) and Dotnet10 Features (runceel/ReactiveProperty, 944 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Okojo Test262?

akeit0 (a GitHub user) maintains it in akeit0/okojo, which has 160 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 21, 2026.

Source: akeit0/okojo on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.