jleechanorg/claude-commands - Page 10

wiki-ingest

Ingest a file into the local LLM wiki and update source/entity/concept pages.

wiki-integrity

Use BEFORE writing wiki/sources, wiki/entities, or wiki/concepts. Routes through /wiki-ingest; bulk generation must also create entity+concept pages.

adjustment-proof

Use when proving, rejecting, or deleting backend adjustment registry entries with real LLM evidence and independent disabled-adjustment worktrees.

ao-operator-discipline

Use when spawning, steering, or auditing Agent Orchestrator workers, especially when the user specifies exact AO parameters such as codex, runtime, project, claim-pr, or PR targets.

ao-worker-dispatch

Checklist for dispatching AO workers — python venv, commit discipline, branch drift, and post-push CodeRabbit verification

dark-factory

Run the Dark Factory DOT pipeline runner against a goal. Slash command: /factory. Implements StrongDM's Attractor pattern as an external Python runner — .dot files are the versioned artifact, sealed holdouts live in a separate repo, every step is recorded to…

factory-spec

Display the Dark Factory pipeline node graphs — spec-review pipelines, factory gates, node types, edge conditions, and handler mappings. Use /factory-spec or /fs to quickly reference the spec graph structure without running a pipeline.

wiki-bfs

Run breadth-first research on a topic and optionally ingest results into the local LLM wiki.

wiki-search

Search the local LLM wiki for matching pages, titles, and content snippets.

ao-model-override

Override the model an `ao spawn` worker uses (e.g. force claude-sonnet-4-6 instead of the project default of wafer.ai/GLM-5.1) WITHOUT mutating ~/.hermes/agent-orchestrator.yaml. Use when the user asks for "claude sonnet with AO", "spawn AO with X model", "AO…

launchd-auto-cleanup

Create macOS launchd cleanup agents with dry-run verification. Writes cleanup script + plist installer, verifies with --dry-run, then installs and runs live.

agents

Reference WorldArchitect agent routing priority and modal lock patterns.

ao-lifecycle-triage

Triage AO lifecycle backfill claim failures and ghost worktree fetch errors.

autor-bench-eloop

Run the autor research and SWE-bench benchmark loop.

autor-n15-loop

Drive the autor phase-three n=15 per technique loop.

babysit-openclaw

Monitor OpenClaw task threads in Slack and nudge on stalls or fabrication.

character-creation-modal-exit

Enforce CharacterCreationAgent modal exit choices and state transition rules.

check-team-worldai-workstreams

Check worldai-workstreams team agents and summarize status, commits, and beads.

firebase-campaign-copy

Copy production Firebase campaigns across users for testing with Admin SDK.

goalexec-define

Define goal criteria without executing — just parse and save

goalexec

Define a goal with success criteria and run autonomous convergence loop until criteria are met

karpathy-wiki

Enforce the Karpathy LLM wiki pattern for ingesting, querying, and organizing sources.

level-up-zfc

DEPRECATED — Redirects to the consolidated ZFC leveling skill

minimax-401-diagnostic

Diagnose and fix MiniMax 401 auth errors in AO workers — the root cause is always a redacted or invalid MINIMAX_API_KEY, not the model name. Use when workers stall at /login, show API Error 401, or when ao-XXXX shows "minimax" in its tmux pane but isn't…

modal-agent-pattern

Design modal agents that cannot be exited until explicit completion choices are selected.

openclaw-diagnostics

Diagnose local OpenClaw gateway model routing, runtime status, and WorldArchitect integration.

streaming-evidence-standards

Define evidence requirements for end-to-end streaming chunk delivery and timing.

tmux-video-evidence

Record captioned terminal evidence videos and publish them as GitHub PR attachments with portable, sanitized outputs

worldai-tools-mcp-proxy-testing

Run and test the WorldAI Tools MCP HTTP proxy with real local harnesses.

zero-touch-metrics

Measure zero-touch and one-touch rates from merged PRs — run in evolve loop cycles

antigravity-computer-use

Use Claude Code to control Google Antigravity IDE on macOS via Peekaboo. Explicitly supports targeting either the Agent Manager window or the Editor window (worktree/editor titles), plus auto routing. Covers workspaces, conversations,…

ao-session-monitor

Properly inspect AO worker tmux sessions to detect working vs idle state

gateway-upgrade

Safe gateway upgrade/downgrade with pre-flight checks, rollback, and post-verification

hook-refire-shortcircuit

Detailed procedures for hook re-fire short-circuit — sentinel files, CR incremental-mode detection, Branch A caps, stale review dismissal commands

llm-json-schema-documentation

Document both INPUT and OUTPUT JSON schemas for LLM-driven features to prevent data flow confusion

mvp-site-app-dev-i6xf2p72ka-uc-a-run-app-root

API skill for mvp-site-app-dev-i6xf2p72ka-uc.a.run.app. Use when: interacting with this site's APIs, automating workflows, debugging requests. Auth: Unknown — capture may reveal auth mechanism.

using-git-worktrees

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

writing-skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

thinclaw

Use thinclaw MCP server — thin inference-less bridge to OpenClaw Gateway for executing tools

validation-gate

Pre-report gate — verifies all planned evidence artifacts exist before writing comparison/validation reports