Overview & result
Elune demonstrates a setup in which Jev selects Claude Code or Codex for a task and supplies typed decisions before risky tool execution. The post describes shadow logging followed by an enforce mode, while the implementation repository remains unverified.
From the original post
Jev just made the Claude Code vs Codex debate obsolete
I connected both to Jev - now the best coding agent is selected for every task, and neither can cross a risky tool boundary without a typed decision
in one run it scanned 247 files, routed the security audit to Claude Code, routed the patch to Codex, passed 18/18 tests and stopped npm publish before execution
here’s how to set it up in 10 min:
task → Jev decision → Claude Code / Codex → tool execution → fresh verification
step 1 → open @typesafeai and create your Jev API key (never paste it into chat)
step 2 → clone and verify the complete agent switch
step 3 → export the key before starting either agent:
export TYPESAFE_API_KEY="YOUR_KEY"
step 4 → test the full decision layer before connecting a live agent:
npm run doctor && npm run check:claude && npm run check:codex
step 5 → connect Claude Code directly from the repository:
claude --plugin-dir .
Claude discovers the plugin and turns Jev review decisions into real confirmation requests
step 6 → for Codex, install the same folder through your local plugin marketplace, open /hooks and trust the exact PreToolUse hook
Codex uses the same policy and safely stops calls that need human review
step 7 → keep agent: auto and the plugin detects Claude Code or Codex automatically - or set agent: claude / codex when you want to lock one runtime
step 8 → start in shadow mode for 20–50 real decisions:
export JEV_AGENT_SWITCH_MODE="shadow" && export JEV_AGENT_SWITCH_LOGGING="true"
your agent keeps working normally while Jev records the route, confidence and outcome without blocking anything
step 9 → switch to enforce only after the decisions look reliable:
export JEV_AGENT_SWITCH_MODE="enforce"
safe calls pass, uncertain calls stop for review, dangerous calls are denied
the default boundary is 0.62 minimum confidence and 0.86 harmful-action probability
step 10 → use it normally - ask Claude Code or Codex to inspect, patch, test or prepare a release; the same Jev layer stays in front of both
the result: Claude Code handles deep repository context, Codex handles fast patches and verification, and Jev decides which worker gets the task - while keeping publishing, production and irreversible actions behind a human boundary
unfortunately, most people are still comparing coding models as if one model needs to win forever
the actual 2030 setup makes the model replaceable: one task enters, Jev selects the best worker, code enforces the decision and every action leaves a receipt
Steal the agent setup everyone will use by 2028, copy the repo below - then read the full Jev Engineering playbook ↓
How Jev fits in the loop
- A coding task is supplied to the routing layer.
- According to the author, Jev chooses a coding worker and evaluates subsequent tool boundaries.
- The integration runs the selected worker and allows, holds for review or denies tool calls according to its policy.
How to reproduce
- Watch the original demo and read the author configuration outline.
- The source describes shadow and enforce modes; the exact public repository was not available in the visible post or replies, so installation and execution have not been reproduced.
Why this build matters
Combines worker routing and tool-call review in one author-described workflow, with explicit uncertainty about reproducibility.
Limitations
- The author refers to a repository but no matching public repository was verified; no GitHub button or copy-and-run instructions are provided.
- The reported run, thresholds and security behavior have not been independently tested.