optim-jev
Claude Code optimization tools from oqura.ai.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/oqura-ai--optim-jev)HTML
<a href="/listings/oqura-ai--optim-jev"><img src="/api/listings/oqura-ai--optim-jev/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
Requirements
- [Claude Code](https://code.claude.com/docs/en/overview) with plugin support - Python 3.10 or newer - A TypeSafe API key for Jev
Install
git clone https://github.com/Oqura-ai/optim-jev.git claude plugin marketplace add ./optim-jev claude plugin install optim-jev@optim-jev
Set the key in Claude Code under `/config` → **TypeSafe API key**, or export it before starting Claude Code:
export TYPESAFE_API_KEY="your-key"
Restart Claude Code. jev-compacter is ready immediately; enable the router and skill picker when you want them. See [Getting started](docs/getting-started.md) for every command, option, and troubleshooting step.
> [!NOTE] > The plugin uses only Python's standard library. Your API key is passed to child processes through the environment and is never written to project files or logs.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 17 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- {
- "name": "optim-jev",
- "description": "Claude Code optimization tools from oqura.ai.",
- "owner": {
- "name": "oqura.ai",
- "url": "https://github.com/Oqura-ai"
- },
- "plugins": [
- {
- "name": "optim-jev",
- "source": "./",
- "description": "Token-usage optimization tools for Claude Code workflows.",
- "version": "0.1.0",
- "license": "MIT"
- }
- ]
- }
README.md · README · 184 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- <div align="center">
- # optim-jev
- **Spend fewer tokens in long agent sessions without changing how you work.**
- Jev-powered optimization for Claude Code, plus model routing for OpenAI Codex.
- [](https://code.claude.com/docs/en/overview)
- [](https://developers.openai.com/codex/plugins)
- [](#license)
- [](https://discord.gg/EpUxGjNBva)
- [Get started](#claude-code-quick-start) · [Codex support](docs/codex.md) · [Documentation](docs/README.md) · [Architecture](docs/architecture.md) · [Contributing](docs/contributing.md)
- <img src="assets/demo.gif" alt="optim-jev demo in Claude Code" width="100%">
- </div>
- ## Why optim-jev?
- <img src="assets/optim-jev.png" alt="optim-jev architecture: context compaction, model routing, and skill selection" width="100%">
- Long agent sessions accumulate stale tool output, send oversized skill catalogs, and use the main model for work a smaller model could handle. Claude Code supports all three optimizers below. Codex supports the model router and an off-by-default advisory skill experiment.
- Each tool works independently and fails open if unavailable. Measured cost reports remain Claude-only.
- ## Three tools, one project
- | Tool | What it does | Available in | Claude default | Learn more |
- |---|---|---|:---:|---|
- | **jev-compacter** | Removes stale tool calls and outputs instead of summarizing away the whole conversation | Claude Code | On | [Guide](docs/jev-compacter.md) |
- | **jev-router** | Runs each subagent, Explore searches included, on the cheapest model that fits, within project rules that evolve with your workflow | Claude Code and Codex | Off | [Guide](docs/jev-router.md) |
- | **jev-skills** | Sends a short, relevant skill list for each prompt instead of the entire catalog | Claude Code; experimental advisory mode in Codex | Off | [Guide](docs/jev-skills.md) |
- <details>
- <summary><strong>jev-compacter — preserve useful context</strong></summary>
- <br>
- <img src="assets/jev-compacter.png" alt="jev-compacter session statistics" width="100%">
- It works automatically with `/compact` and auto-compaction. Inspect the current session with:
- ```text
- /jev-compact stats
- ```
- Want it to prune earlier or keep more? Pick a **Compaction: style** (`balanced`, `save-tokens`, or `keep-context`) in `/config` under optim-jev. See [Pick a style](docs/jev-compacter.md#pick-a-style).
- </details>
- <details>
- <summary><strong>jev-router — the right model for every subagent</strong></summary>
- <br>
- <img src="assets/jev-router.png" alt="jev-router model routing decisions" width="100%">
- Your main conversation keeps its model, so its prompt cache stays warm. The routing happens where it pays off: every subagent Claude spawns gets its own model and effort from Jev, Explore searches included. A quick lookup runs on haiku; a deep architecture review gets a stronger model.
- Claude works as usual, editing directly and delegating when a task calls for it or when you ask. `rules.json` sets which models may edit each path; when a path needs a different model than your session's, Claude hands that change to a routed subagent.
- ```text
- /jev-route init "what matters in this project"
- /jev-route on | off
- /jev-route why | stats
- ```
- Tell Claude to change a preference later—for example, “let haiku edit the tests”—and the project rules update with your workflow.
- </details>
- <details>
- <summary><strong>jev-skills — load only relevant skills</strong></summary>
- <br>
- <img src="assets/jev-skills.png" alt="jev-skills prompt shortlist" width="100%">
- ```text
- /jev-skills on | off
- /jev-skills scope project | global
- /jev-skills why | stats | reindex
- ```
- </details>
- ## Claude Code quick start
- ### Requirements
- - [Claude Code](https://code.claude.com/docs/en/overview) with plugin support
- - Python 3.10 or newer
- - A TypeSafe API key for Jev
- ### Install
- ```bash
- git clone https://github.com/Oqura-ai/optim-jev.git
- claude plugin marketplace add ./optim-jev
- claude plugin install optim-jev@optim-jev
- ```
- Set the key in Claude Code under `/config` → **TypeSafe API key**, or export it before starting Claude Code:
- ```bash
- export TYPESAFE_API_KEY="your-key"
- ```
- Restart Claude Code. jev-compacter is ready immediately; enable the router and skill picker when you want them. See [Getting started](docs/getting-started.md) for every command, option, and troubleshooting step.
- > [!NOTE]
- > The plugin uses only Python's standard library. Your API key is passed to child processes through the environment and is never written to project files or logs.
- ## OpenAI Codex support — new
- Start with the complete [Codex guide](docs/codex.md) for installation, usage, model-tier setup,
- verification, limitations, troubleshooting, and uninstall steps.
- optim-jev can automatically route each Codex subagent to an account-specific `fast`, `balanced`, or
- `strong` model. It also selects reasoning effort, applies project path rules, escalates after
- failures, and can provide an optional advisory skill shortlist. Claude and Codex keep separate
- model catalogues, policies, caches, and logs.
- > [!IMPORTANT]
- > **Compaction is not supported in Codex.** Codex hooks cannot replace live conversation history.
- > The AbovePrompt dashboard, slash commands, and measured token and cost reports are also
- > Claude-only.
- ### Install and use
- Codex CLI 0.162.1 or newer can install optim-jev directly from GitHub. No PyPI release or manual
- clone is required.
- ```powershell
- py -3 -m pip install "https://github.com/Oqura-ai/optim-jev/archive/refs/heads/main.zip"
- optim-jev codex install
- $env:TYPESAFE_API_KEY = "your-key"
- cd C:\path\to\your-project
- optim-jev codex setup
- optim-jev codex status
- codex
- ```
- On the first Codex launch after install or update, run `/hooks`, review and trust every optim-jev
- hook, then restart Codex.
- Inside Codex, subagent routing is automatic. Check the most recent decision or control project
- features with:
- ```text
- !optim-jev codex why
- !optim-jev codex status
- !optim-jev codex on
- !optim-jev codex off
- !optim-jev codex skills-on
- !optim-jev codex skills-off
- ```
- ## Documentation
- | Resource | What you will find |
- |---|---|
- | [Getting started](docs/getting-started.md) | Installation, configuration, commands, and troubleshooting |
- | [Codex support](docs/codex.md) | Codex installation, router setup, configuration, and limitations |
- | [TinyCart demo](demo/tinycart/DEMO.md) | A short, repeatable showcase of all three tools on a toy project |
- | [Performance metrics](docs/performance-metrics.md) | How token usage, cost, and estimated savings are calculated |
- | [Architecture](docs/architecture.md) | The TypeScript-to-Python bridge, data flow, and session logs |
- | [Contributing](docs/contributing.md) | Local setup, tests, conventions, and pull requests |
- ## Community and support
- - Found a bug or have a feature idea? [Open an issue](https://github.com/Oqura-ai/optim-jev/issues/new/choose).
- - Want to help? Read the [contributing guide](docs/contributing.md) and submit a focused pull request.
- - For the wider Claude Code community, join the official [Claude Developers Discord](https://anthropic.com/discord).
- ## License
- optim-jev is released under the MIT License.
- <div align="center">
- Built by [Oqura.ai](https://github.com/Oqura-ai) for more efficient coding-agent workflows.
- </div>
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.