Skip to content
Development
Command

/d

Jev-validated router: the session picks the route with /do's rules; Jev answers the attachment questions and checks the restated intent.

From plugin
vexjoy-agent
44912 skills198 agents12 commands83 hooks
$ npx -y skills add notque/vexjoy-agent --agent claude-code

Command definition

d.md
description: "Jev-validated router: the session picks the route with /do's rules; Jev answers the attachment questions and checks the restated intent."
argument-hint: "[request]"
allowed-tools: ["Read", "Bash", "Grep", "Glob", "Skill", "Task"]

/d - Jev-validated Router

Route user requests with `/do`'s rule text and manifest, then use Jev to attach domain skills and check that the restated outcome survives the route. Use `/d` to A/B-test against `/do`; use `/do` for normal work.

Instructions

Call the Skill tool with `d`. Follow its classify, decide, enhance, and execute phases.

Base directory: $CLAUDE_PROJECT_DIR or the current working directory
Skill file: skills/meta/d/SKILL.md

**Phase 1: CLASSIFY** — `scripts/jev-route.py` runs the force-route guard and one Jev attachment evaluation. You pick the agent, skill, and pipeline with `/do`'s rules (`scripts/print-route-rules.py`) and the routing manifest, then `jev-route.py --finalize` validates the pick and adds the attachments. **Phase 2: ALIGN INTENT** — MANDATORY before any banner or dispatch. Write `PROPOSED_INTENT` for the finalized route, run `jev-intent-align.py` on it. **Phase 3: DECIDE** — Show the finalized route. Display the routing banner only after Phase 2 completes. **Phase 4: ENHANCE** — Map stack signals to concrete stack entries. **Phase 5: EXECUTE** — Same Task Spec + `build-dispatch.py` contract `/do` uses, reused unmodified.

The routing banner MUST include the Phase 2 intent alignment result:

===================================================================
 ROUTING (/d): [brief summary]
===================================================================

 Intent (/d):
   -> Restated: [PROPOSED_INTENT]
   -> Alignment: [aligned|review|unavailable] [— issues, if any]

 Selected:
   -> Agent: [name] - [reasoning]
   -> Skill: [name] - [reasoning]
   -> Source: [session|pre-route-force] (confidence: [level])

 Invoking...
===================================================================

A banner printed without the `Intent` block means Phase 2 was skipped — that is not allowed.

For the full design (why `/d` exists as a separate command, the request/response contract, measured eval results), read `skills/meta/d/SKILL.md` and `skills/meta/d/references/jev-classifier-design.md`.

ARGUMENTS: $ARGUMENTS

Read more
@notque
Ships withvexjoy-agent

Essays and writing behind this toolkit live at vexjoy.com. VexJoy Agent connects plain-English requests to specialist agents, skills, and workflows. /do selects the knowledge and tools needed for your task.

44964 skills198 agents
Get the whole plugin

Stars on GitHub

Momentum

stars in total
449
Star history of notque/vexjoy-agent on GitHub, a chart by star-history.com

Other commands on vexjoy-agent.

do

do

Command

Smart router: classify requests and route to the correct agent + skill

@notque@notqueInstall Command
github-profile-rules

github-profile-rules

Command

`github-profile-rules` — extract programming rules and coding conventions from a GitHub user's public profile via API.

@notque@notqueInstall Command

More commands from other plugins.

build
Auto-invoked

build

Command

Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.

@addyosmani@addyosmaniInstall Command