菜单
Optional local install of fluxctl CLI and AGENTS.md/legacy CLAUDE.md instructions. Use when user runs /flux:setup. Triggers on literal `/flux:setup`.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Create structured build plans from feature, bugfix, upgrade, or refactor requests, or from Flow IDs. Use when planning implementation after the workflow envelope is explicit. Triggers on /flux:plan with text descriptions or Flow IDs (fn-1-add-oauth, fn-1-add-oauth.2, or legacy fn-1, fn-1.2, fn-1-xxx, fn-1-xxx.2).
Stakeholder-facing feature proposal flow. Guides non-technical team members through a conversational planning session — probes for business context, pushes back like an engineer, estimates complexity and cost, then documents the proposal and creates a PR for engineering handoff. Triggers: /flux:propose, or detected implicitly when a non-technical user describes a feature, bugfix request, or upgrade without implementation detail during /flux:scope or /flux:plan.
Use when scoping a new feature, bugfix, upgrade to an existing feature, or refactor into a concrete Flow objective. Guides Start, Discover, Define, Stress Test, Future Pressure, Develop, Deliver, and Handoff; requires an explicit shallow-vs-deep choice before scoping continues. Triggers on literal `/flux:scope`, including prompts like `/flux:scope Add OAuth login` or `/flux:scope fn-1 --deep`.
Manage .flux/ tasks, epics, and config. Triggers: 'show me my tasks', 'list epics', 'what tasks are there', 'add a task', 'create task', 'what's ready', 'task status', 'show fn-1-add-oauth', 'show my Flux config', 'what did setup configure', 'edit Flux settings'. NOT for /flux:plan or /flux:work.
Execute a Flow epic or task systematically with git setup, task tracking, quality checks, and commit workflow. Use when implementing a plan or working through a spec. Triggers on literal `/flux:work` prompts with Flow IDs (fn-1-add-oauth, fn-1-add-oauth.2, or legacy fn-1, fn-1.2, fn-1-xxx, fn-1-xxx.2).
Use when contributing fixes to Flux itself or deciding whether a reported Flux issue actually needs a PR. Reproduce first, exhaust setup/workaround causes, and only create a PR for verified product bugs. Triggers on literal `/flux:contribute` and requests like "report a Flux bug" or "contribute a fix to Flux".
| name | flux-setup |
| description | Optional local install of fluxctl CLI and AGENTS.md/legacy CLAUDE.md instructions. Use when user runs /flux:setup. Triggers on literal `/flux:setup`. |
| user-invocable | false |
Install fluxctl locally and add instructions to project docs. Fully optional - Flux works without this local setup, but this is the preferred path for Codex-first repos.
On entry, set the session phase:
PLUGIN_ROOT="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}}"
[ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(ls -td ~/.claude/plugins/cache/nairon-flux/flux/*/ 2>/dev/null | head -1)
FLUXCTL="${PLUGIN_ROOT}/scripts/fluxctl"
$FLUXCTL session-phase set setup
On completion, reset:
$FLUXCTL session-phase set idle
fluxctl accessible from command line (add .flux/bin to PATH)AGENTS.md, and Flux can keep a legacy CLAUDE.md mirror when neededdiffity CLI install during setup so tours work immediatelyCRITICAL: Read the ENTIRE workflow.md before starting execution. The workflow is ~2000 lines across 10+ steps. The most common failure is reading the first few steps, starting execution, and never reaching the configuration questions (Step 6), business context (Step 5b), or docs block update.
A step completion checklist and verification gate at the end of workflow.md will catch skipped steps — but prevention is better than detection. Read it all first.
.mcp.json, .flux/, .flux/brain/). Supported skill installs now go into PlaTo's .secureskills/ store, with loose .codex/skills/ / .claude/skills/ folders retained only as compatibility fallbacks when needed/flux:prime first before feature work/flux:reflect at session endALWAYS run at the very end of /flux:setup execution:
PLUGIN_ROOT="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}}"
[ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(ls -td ~/.claude/plugins/cache/nairon-flux/flux/*/ 2>/dev/null | head -1)
UPDATE_JSON=$("$PLUGIN_ROOT/scripts/version-check.sh" 2>/dev/null || echo '{"update_available":false}')
UPDATE_AVAILABLE=$(echo "$UPDATE_JSON" | jq -r '.update_available')
LOCAL_VER=$(echo "$UPDATE_JSON" | jq -r '.local_version')
REMOTE_VER=$(echo "$UPDATE_JSON" | jq -r '.remote_version')
UPDATE_CMD=$(echo "$UPDATE_JSON" | jq -r '.update_command // "Update Flux from the same source you installed it from, then restart your agent session."')
If update available, append to output:
---
Flux update available: v${LOCAL_VER} → v${REMOTE_VER}
${UPDATE_CMD}
---