jleechanorg

Control cmux tabs, workspaces, and terminal panes via Unix socket. Use when reading terminal output, sending commands to another agent's pane, switching tabs, or monitoring coder progress.

Read and steer another cmux terminal tab through the Unix socket.

Spawn or respawn a persistent, crash-recoverable Sonnet sidekick for ANY long-running mission — PR/CI fleets, research sweeps, migrations, monitoring, ops runbooks, data pipelines, multi-day projects in any repo or no repo at all. The sidekick is ALWAYS a named in-session Claude Agent-Team teammate (model sonnet, SendMessage-addressable, visible in the user's panel) durable via STATE.md + a P1 resumption bead + commit-often. There is NO tmux mode and NO codex engine — external tmux sidekicks and -p print-mode sidekicks are banned. Use when the user says /sidekick, "respawn the sidekick", or wants long work to survive conversation crashes.

Orchestrate multi-agent swarms (ultracode Workflow fan-outs + Agent-team lanes) with adversarial verification, /innov, /advice, and a sidekick durability layer for crash-recoverable runs

Audit automation job runs, logs, PR processing metrics, and AI-authored remote commits.

Aside browser is the PRIMARY browser tool for all Hermes/Claude/Codex work. Use aside CLI (repl/mcp/exec modes) or aside-mcp before Playwright MCP / superpowers-chrome. Use when opening browsers, scraping, UI tests, localhost verification, cookie injection flows, or any browser-driven automation. Playwright MCP and superpowers-chrome are explicit fallbacks for cases Aside can't handle (e.g., headless CI runners, Playwright-specific test fixtures). Reversible — see ~/.hermes/scripts/rollback-aside-default.sh.

End-to-end auto-factory driver — picks up beads + GH issues tagged factory, dispatches coders to drive worldai PRs to /green + /advice + /er, runs verifier ticks, repeats until done. Designed to work even when GH API is rate-limited (falls back to beads-only).

Capture browser traffic with Playwright and generate Python client + MCP tool artifacts from HAR sessions.

Use when dispatching work through the Hermes gateway with /claw, especially when the task may resolve slash commands or hand off into AO worker orchestration.

12-hour autonomous evolution loop — observe, measure, diagnose, fix, repeat every 10min. Drives zero-touch rate up by finding friction and dispatching fixes.

Custom evolve loop for jleechanbrain orchestrator — drains dropped Slack thread backlog via /claw, fixes hermes issues, proposes new work items. Max 50 items, newest-first.

jleechanbrain / Hermes-specific harness — gateway, canary, deploy, lane backlog, staging vs prod. Use with user-scope harness-engineering.

Delegate coding change tasks to Agent-Orchestrator (AO). Triggered by the keyword "agento" anywhere in a message, or by default for any coding task. Never use mctrl unless explicitly requested.

Spawn an Agent-Orchestrator (AO) worker that uses the minimax CLI with the M3 model (via the minimax Anthropic-compatible API). Use when: the task should be dispatched to a worker that uses minimax M3 specifically, when the user says 'use minimax', 'use the M3 model', 'use the minimax worker', 'ao spawn minimax', or 'minimax CLI for AO'. This skill verifies the env (MINIMAX_MODEL, MINIMAX_API_KEY, ANTHROPIC_BASE_URL) end-to-end, then runs `ao spawn --agent minimax`. Verified 2026-06-13 against session ao-6355 / PR #678.

Enforce headless browser automation by default for Hermes — Playwright MCP and superpowers-chrome. Use when opening browsers, scraping, UI tests, localhost verification, or any chrome_use_browser / Playwright call. Never headed unless Jeffrey explicitly requests visible browser.

Use the browserclaw CLI to capture browser traffic, infer API endpoints, generate Python clients, OR decrypt + inject Chrome cookies for session reuse. Use when asked to reverse-engineer a website, generate an API client from a HAR, or reuse a logged-in Chrome session in a Playwright browser.

Multi-PR triage and parallel work dispatcher. Prevents single-PR tunnel vision by enforcing a survey-before-deep-dive protocol.

Canonical 6-green PR merge criteria, PR status check pattern, PR freeze discipline, and admin merge protocol

Watch one or more AO worker tmux sessions, classify their state (WORKING/IDLE/QUEUED/DEAD/COMPLETED), auto-remediate known failures (trust TUI), and push-notify on STALLED-COMPLETED / DEAD sessions. Reuses ao-session-monitor state detection. Use /babysit to start a monitoring loop on a specific worker, all active workers, or workers matching a PR/branch.

Codex-native AO evolve loop. Run a deterministic local observe/measure cycle, then optionally delegate targeted fixes via /claw using the canonical evolve-loop skill.

Use after every `git push` on a PR — enumerates ALL current gate failures, fixes ALL in one local pass, and pushes once. The fix-all-before-push invariant. Pairs with the CLAUDE.md PR driver loop contract and babysit DRIVER mode.

Evidence standards for testing and verification, including evidence classes, mock/real boundaries, and proof bundle requirements.

Classifies GitHub issues/PRs into PR-type categories and recommends autor techniques. Used by packages/core/src/decomposer.ts.

Use this skill when working in repositories managed by Agent Orchestrator or when the user asks how to use `ao` properly. Covers the default AO workflow: bootstrap with `ao start`, dispatch work with `ao spawn`, inspect progress with `ao status` or `ao session ls`, steer sessions with `ao send`, and recover or clean up sessions safely.

Use when a user asks why a disk is filling, what uses its capacity, what grew over time, or what can be safely reclaimed.

Use when checking local disk capacity, investigating disk growth, or reviewing safe cleanup candidates.

Use when diagnosing why a disk is full, what consumes its capacity, what grew over time, or what may be safely reclaimed.

Use when diagnosing disk capacity or growth and when previewing repository-gated cache, temp, or worktree cleanup.

Use when a Codex agent needs disk usage diagnosis, growth history, or repository-gated cleanup guidance.

Workstation maintenance and growth analytics tool for Hermes.

Openclaw disk diagnostic, growth regression tracker, and automated cleanup tool.

End-to-end auto-factory driver — picks up beads + GH issues tagged factory, dispatches coders to drive worldai PRs to /green + /advice + /er, runs verifier ticks, repeats until done. Designed to work even when GH API is rate-limited (falls back to beads-only).

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 CXDB, and the Healer clusters failures into diagnoses. Use when you want the goal_harness idea executed as a reproducible external pipeline instead of in-Claude subagent dispatch.

Dark Factory two-phase spec workflow (/factory-spec, /fs): create a main spec (spec.md) AND an attractor spec (attractor_spec.md) via the spec_gen pipeline, review an existing spec of either kind, or display the pipeline node graphs — spec-review pipelines, factory gates, node types, edge conditions, handler mappings. Create mode runs dark-factory --pipeline slim/spec_gen.dot; both the main and attractor specs must be codex-cold-reviewed and pass before exit. Review and show modes are in-session only.

Build a developer reproduction bundle for agent-review failures, missed-plan retrospectives, Claude/Codex transcript comparisons, or cases where Anthropic/OpenAI engineers need raw conversation JSONL, subagent state, repo evidence, hashes, and a concise replay guide.

Run matched A/B reviewer calibration for /f: compare factory reviewer, raw codex exec, and delegated subagent reviews on the same frozen PR/work-item envelope.

Assess wiki against Karpathy pattern standards

Search across all memory systems — ~/roadmap, beads, claude memories, hermes sqlite (audit log), hermes briefings, hermes index, openclaw memories, wiki, and conversation history. Use whenever the user asks to search memories, find something in memories, or looks for anything that might have been captured in any memory store. Trigger on: 'search memories', 'find in my memories', '/ms', '/memory_search', 'search across all memories', 'look up in memory', 'did I save this somewhere', 'do I have anything about X in memory'.

Dependencies required for /secondo command

How to read API keys (OpenAI, Anthropic, Gemini, Perplexity, OpenRouter, Grok) from GCP Secret Manager. Ported from jleechanorg/ai_universe.

The user-facing entry point for AI Universe Lite — turn a natural-language prompt into a shareable, self-contained MCP gem.

Use when starting any creative work — a brainstorming partner that explores intent, requirements, and design before any code is written.

Diagnose ez-gh-actions (ezgha) fleet health using the repo's doctor-runner script and named remediation steps. Use when ezgha.service is misbehaving, the runner fleet is degraded, or "GitHub Actions not running" complaints land on ezgha.

Install ez-gh-actions (ezgha) and diagnose runner problems (docker daemon, gh auth, JIT registration, service, disk floor, VM containment)

Scrape browser traffic with Playwright → infer API endpoints → generate Python client + MCP tools artifacts.

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.

Use the local spicy_llm Ollama/Heretic setup for decensoring, refusal-rate, and erotica/censorship evidence tests.

Debug REST/GraphQL APIs: status codes, auth, schemas, repro.