orchestrator
claudeOne view over every local Claude Code session: task pools with evidence, child sessions under their parent task, a TUI, and /orch for your phone.
1 skill · 1 command · hooks
Feature work in one flow: requirements in rounds, one design doc carrying every decision, code gated on that doc, UI critiqued before it ships, analytics asked about at the hand-offs.
Plugin devflow from marketplace claude-skills in Cybeaster/LLMSkills. Commands read from the repo's manifest — 21 days 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.
designUse when the requirements of a feature are settled and it needs its design, in place of superpowers:brainstorming for that step - devflow:requirements (or `requirements` where the project vendors devflow) handed off with "decisions settled", or the user points at a spec with ## Решения and asks for
requirementsUse when the user wants to work out a new feature or a change to how a product behaves - its requirements, a spec, a design doc - before plans or code, in place of grilling or superpowers:brainstorming when the subject is such a feature. Triggers - "new feature", "grill me" or "brainstorm" about a f
bash "${CLAUDE_PLUGIN_ROOT}/hooks/devflow.sh" prompt
bash "${CLAUDE_PLUGIN_ROOT}/hooks/devflow.sh" skill
bash "${CLAUDE_PLUGIN_ROOT}/hooks/devflow.sh" edit
bash "${CLAUDE_PLUGIN_ROOT}/hooks/devflow.sh" bash
bash "${CLAUDE_PLUGIN_ROOT}/hooks/devflow.sh" stop
bash "${CLAUDE_PLUGIN_ROOT}/hooks/devflow.sh" end
One view over every local Claude Code session: task pools with evidence, child sessions under their parent task, a TUI, and /orch for your phone.
1 skill · 1 command · hooks
Skills for learning to code: mentoring a beginner through building their first project, and explaining unfamiliar codebases from zero.
2 skills
Writing skills: ru-style writes, checks, fixes and scores Russian text — «Пиши, сокращай» (Ильяхов, Сарычева) plus the ru-text rule set.
1 skill
Picks the model and effort for delegated work by task class, enforces it on Agent calls, and logs every choice.
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.