Command
Spawn N concurrent /ai-sdlc execute sessions in tmux panes (max 5). Reads the dispatch-ready frontier, presents top N candidates, asks operator to confirm, then fires one tmux window per task. Coordination via .ai-sdlc/dispatch/sessions/. Resource-gated: refuses if available memory = ncpu. AISDLC-462.
Command
Execute a backlog task OR GitHub issue end-to-end — worktree → developer subagent → 3 parallel reviewer subagents → PR. Runs inline in the main Claude Code session so the Agent tool is available without a subagent middleman.
Command
Import a spec-kit feature into the backlog. Reads tasks.md and writes one backlog task per upstream entry with specRef: back-references (RFC-0036 Phase 4 / AISDLC-329).
Command
Generate this contributor's ed25519 signing key for review attestations. Run once per machine before /ai-sdlc execute.
Command
Run one autonomous orchestrator tick in the current Claude Code session as Conductor (RFC-0041 §4.2).
Command
Show AI-SDLC pipeline status for the current branch or a specific issue/task.
Command
/ai-sdlc rebase — auto-rebase a PR onto latest main, resolve mechanical conflicts, force-push with --force-with-lease, re-sign attestation if contentHash changed.
Command
/ai-sdlc resolve-conflicts — manually invoke the ci-conflict-resolver agent against a single PR. Phase 1 surface (AISDLC-460) for the same agent the ci-failure-watcher dispatches automatically. Use when CI failed on a stale base and you'd like the rebase + re-arm to happen now rather than waiting for the next watcher…
Command
Run AI-SDLC review agents on a pull request (testing + critic + security).
Command
Scaffold a new adopter RFC from the framework template (RFC-0036 Phase 2 / AISDLC-327).
Command
Score and triage an issue with the RFC-0008 admission composite (PPA + pillar breakdown). Auto-detects GitHub or Backlog.md.
Command
Show installed vs latest ai-sdlc plugin version. Bypasses the 24h SessionStart cache.
Skill Claude CodeCodex
Apply a rigorous decision rubric when asking the user for a non-trivial design, architectural, or policy choice via AskUserQuestion. Replaces shallow "do you agree with the author's recommendation?" prompts with a full problem statement → industry research → 3-4 options with tradeoffs → recommendation +…