Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Jev

ASecurity

Hand a task to Claude Opus 5.5 running under jev-opus, where the TypeSafe Jev reflex re-picks the effort level (low/medium/high) before every step without breaking the prompt cache. Use when the user asks to run something "with jev", "through jev-opus", or wants effort tuned automatically per step.

4 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsbashnodeapi

Works with

claude codeapi

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add WXK-AI/jev-opus --skill jev --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Jev?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Jev
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/wxk-ai-jev/badge)](https://www.skillsdirectory.com/skills/wxk-ai-jev)

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: jev
description: Hand a task to Claude Opus 5.5 running under jev-opus, where the TypeSafe Jev reflex re-picks the effort level (low/medium/high) before every step without breaking the prompt cache. Use when the user asks to run something "with jev", "through jev-opus", or wants effort tuned automatically per step.
argument-hint: <task to hand off>
allowed-tools: Bash
---

# Hand a task to jev-opus

jev-opus runs the task in a **separate** Claude Code process on `claude-opus-5-5`. Jev picks that session's effort when the task starts and again after every tool batch. It cannot change the effort of the session you are in now; that is by design in Claude Code.

## Run it

Pass the task through a quoted heredoc, so no quoting in the task can break the command. Run it from the user's project directory, **in the background** (tasks can take many minutes), and wait for it to finish:

```bash
npx -y jev-opus@latest --permission-mode auto -w "$PWD" <<'JEV_TASK'
$ARGUMENTS
JEV_TASK
```

If `$ARGUMENTS` is empty, ask the user what task to hand off instead of running anything.

Add flags only when the user asks for them: `--max <low|medium|high|xhigh|max>` raises the effort ceiling (default `high`); `--effort <level>` pins one level; `-v` shows every routing reason and per-call cache stats.

## Report back

When it finishes, tell the user:
- what jev-opus did, and its final answer, briefly and in your own words
- the `effort path:` line (for example `medium → low → high×2`) and the `cache:` line
- the cost line

Do not redo or re-verify the work yourself unless the user asks.

## If it fails

- `JEV_API_KEY not set`: the run still works, using local heuristics. Tell the user to run `npx -y jev-opus@latest init` to add their TypeSafe Jev key.
- `Not logged in`, or an authentication error: the user needs to run `claude auth login`, or set `ANTHROPIC_API_KEY` in `~/.config/jev-opus/.env`.
- Node older than 22.18: jev-opus needs Node ≥ 22.18.
- Anything else: show the error and suggest `npx -y jev-opus@latest doctor`.

Attribution

WXK-AIWXK-AI
View sourceMore from WXK-AI →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

695601 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →