dev-loop
claudecodexAutomated development loop and ad-hoc workflow generation for orchestrating AI coding agents
3 commands
Asks Jev (via OpenRouter) how long each job will run and, in Claude Code, whether a fresh subagent would do it cheaper. Starts in shadow mode. Off until you turn it on with /jev on.
Plugin jev-router from marketplace yorrick in yorrick/agent-skills. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
jevSwitch the Jev model router on or off, set its Claude Code mode, run its fork check, or show its status. Use when the user types /jev, $jev, "jev on", "jev off", "jev status", "jev mode", asks to turn the Jev router on or off, asks how many messages went to each size, asks what Jev has cost, or asks
everydayJev router helper for everyday jobs (a normal email, post or short document, or a small, well-defined code change or bug fix). Runs on Claude Opus 5.5 at low thinking. Use only when the Jev router hands you a job.
hardestJev router helper for hardest jobs (strategy, architecture or data design, or anything where a wrong call is expensive). Runs on Claude Opus 5.5 at max thinking. Use only when the Jev router hands you a job.
largeJev router helper for large jobs (a multi-step build, research, a full report, or a feature that spans several files). Runs on Claude Opus 5.5 at high thinking. Use only when the Jev router hands you a job.
tinyJev router helper for tiny jobs (a lookup, a rename, a one-line answer or a one-line code change). Runs on Claude Haiku 4.5. Use only when the Jev router hands you a job.
uv run --quiet --script "${CLAUDE_PLUGIN_ROOT}/skills/jev/scripts/jev_router.py" hook claude
Automated development loop and ad-hoc workflow generation for orchestrating AI coding agents
3 commands
Analyzes session transcripts and improves project documentation (CLAUDE.md, README, memory) based on learnings
1 skill · hooks
Monitor and steer Claude Code, Codex, and other terminal coding agents through tmux panes.
1 skill
Create clear process flowcharts and interactive walkthroughs, with evidence-based layout guidance and keyboard checks for the actual delivery surface.
1 skill
Multi-provider interactive PR code review. Runs Claude Code, Gemini CLI, and Codex CLI in parallel, merges findings, then lets you vet each issue before posting to GitHub.
1 skill
Access-control rules for Supabase projects exposed directly to a browser via PostgREST. Covers the three enforcement layers (GRANT, RLS, triggers), the traps that cause privilege escalation, and how anon keys, JWTs and service_role actually differ.
1 skill
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Token usage tracking, model cost attribution per agent, budget alerts, and optimization recommendations
24 skills · 1 command · 1 agent · hooks
Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.
1 skill
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Cloud architecture design for AWS/Azure/GCP/OCI, Kubernetes cluster configuration, Terraform infrastructure-as-code, hybrid cloud networking, and multi-cloud cost optimization
8 skills · 7 agents
Core financial modeling and analysis tools: DCF, comps, LBO, 3-statement models, competitive analysis, and deck QC
13 skills · 7 commands · 12 MCP servers
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.