jleechanorg-claude-commands

Plugin jleechanorg-claude-commands from marketplace cascade-code-general-misc-2 in joshuarweaver/cascade-code-general-misc-2. Commands read from the repo's manifest — 1 month ago.

Skills (200)

• 4layer

  /4layer - Four-Layer Minimal Repro Testing Protocol

• accept-adapt-reject

  Triage incoming feedback into Accept / Adapt / Reject buckets with structured verdicts and follow-up actions. Triggers on /aar, /accept-adapt-reject, or review triage.

• adjustment-proof

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

• advice

  Token-efficient second opinion slash command /advice. Extracts the decision point plus a pointer to the change (PR / ref / paths) so each reviewer reads the code itself, then fans out in parallel to up to four reviewers: (1) Codex + Opus CLI reviewers launched concurrently as the primary pair, (2) f

• agent-orchestrator

  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

• agento-report

  Generate a full agento PR status report — draft readiness, canonical /green, zero-touch rate, inline display, and Slack summary.

• agents

  Apply WorldArchitect.AI agent-routing priority, modal-lock, and stale-state guard patterns.

• ai-universe-auth

  Authenticate with AI Universe MCP server for multi-model commands

• ai-universe-httpie

  Use HTTPie to call AI Universe MCP server for multi-model analysis

• ai-universe-second-opinion-workflow

  Complete workflow for using AI Universe MCP /secondo command

• 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, Knowledge/Browser/Settings panels, keyboard shortcuts, model sele

• ao-lifecycle-triage

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

• 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 worker but not GLM", or any one-shot mod

• 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-session-monitor

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

• ao-spawn-gate

  Pre-spawn checklist for Agent Orchestrator worker dispatch.

• ao-spawn-safety

  Use BEFORE bulk or iterative AO spawns over 3 workers. Respect the channel max_spawn setting, enforce the absolute 30-worker cap, spawn at most 15 per batch, and never use load average as the gate.

• ao-worker-dispatch

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

• aside-browser-default

  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. Pl

• auto-factory

  Use when the user explicitly invokes /af or /auto-factory for a coding task.

• auto

  Use when /auto is requested for the established review-and-push sequence.

• auton

  Diagnose why the automation system is not autonomously completing draft readiness and driving PRs to green. Invoked by `/auton`; measures canonical zero-touch readiness, detects stale sessions, and reviews worker outcomes.

• babysit-openclaw

  Monitor OpenClaw Slack tasks for stalls or fabricated progress and nudge them safely.

• backend-first

  Use when fresh backend behavior needs deterministic proof, root-cause-first routes a failure to the backend lane, or an acceptable model response changes or disappears after the provider boundary.

• backup-verification

  Use whenever asked whether "the backup" is working, or after invoking scripts/backup-home.sh or any multi-target backup script, or when detecting config drift, missing files in repo, rsync failures, or /green-style verdicts that depend on backup state. Mandates per-target verification rather than tr

• bashrc

  Safe wrapper and settings editing playbook for ~/.bashrc — hardening protocol for editing Claude/claude CLI wrappers and model routing without breaking base claude behavior. Slash command: /bashrc.

• bead-followup-templates

  Standardize br bead follow-ups for PR reviews and code reviews so each bead includes exact implementation instructions, API/function signatures, and acceptance criteria.

• beads-issue-tracking

  Use when creating, querying, updating, closing, syncing, or diagnosing Beads issues with the br CLI.

• benchg

  Genesis vs Ralph orchestrator benchmark — runs both orchestration systems on the same project spec in isolated tmux sessions, then compares quantitative metrics (files, LOC), runs a consensus code review, does live build/test validation, and produces a benchmark report. Slash command /benchg [projec

• bq-evidence-reading

  Use this when reviewing WorldArchitect PR evidence that claims real LLM request/response logging, token counts, RAG/shadow comparison, or BigQuery provenance.

• browser-control

  Control real websites and authenticated browser sessions, inspect pages, complete approved UI flows, or troubleshoot browser automation. Use for general browser work, site settings, OAuth consent, existing tabs, and Slack app configuration. Uses Aside first and routes deterministic app testing to pl

• browser-testing

  Use when testing localhost URLs or web UIs. PRIMARY: aside browser (CLI / aside-mcp). FALLBACK: mcp__playwright-mcp (headless); forbids mcp__claude-in-chrome__* (requires extension).

• browserclaw

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

• 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.

• bypass-claims

  Bypass-claim evidence standards for any fast-path, short-circuit, LLM skip, template bypass, or cache hit claim in this repo.

• callpath

  General read-only execution tracer. Profiles automate known systems; without a profile the LLM must fresh-investigate entry→hops→blocker from live evidence. Triggers on /callpath, trace execution, where stuck.

• character-creation-modal-exit

  Enforce the WorldArchitect.AI character-creation modal exit protocol and routing lock.

• claude-code-computer-use

  Use Claude Code to run computer-use style UI automation loops with screenshot → decide → act cycles, safety guardrails, and step-bounded execution. Trigger when the user asks to make agents do Claude computer-use behavior, desktop/browser UI control, click/type/scroll automation, or iterative visual

• claw-dispatch

  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.

• cloud-ops-credential-guard

  Securely guide teammates through cloud configuration, secrets management, and incident triage

• cmux-backup

  Backup all cmux workspaces, surfaces, and their current working directories via the socket API. Produces a timestamped JSON snapshot at ~/.cmux-backups/.

• cmux-goal

  Set Claude Code's builtin /goal for yourself (the running session) via the cmux socket CLI — types the /goal command into your own composer so the Stop hook + purple UI indicator activate. Use when the user asks you to set your own goal, when /ironclad step 3 needs the builtin set, or when a mission

• cmux-steer

  Resolve, inspect, and safely steer named cmux workspaces, tabs, and surfaces.

• code-centralization

  Investigate existing utilities before adding code to avoid duplication and centralize shared behavior.

• code-quality

  Metric-driven PR code quality review (Short variant for small PRs, Long variant for important/architectural/AI-generated PRs). Cyclomatic / cognitive complexity, duplication, coupling/cohesion, package metrics, code smells, lightweight security patterns, AI-import verification gap. Cite file:line ev

• code-review

  Review PRs, branches, commits, or working changes for actionable correctness and standards findings, including focused rechecks of known blockers.

• code-standards

  User-scope code/diff/PR review against the user-wide standards — ZFC, ZFC leveling, root-cause-first, and the ponytail (lazy senior dev) ladder. Dispatched by the /code-standards command.

• coderabbit

  Post "@coderabbitai all good?" comment on the PR associated with the current branch

• command-research

  Empirical Command & Skill Usage Research Protocol — Measure true human vs agentic slash command invocations across Hermes, Claude Code, and Codex session stores without substring noise

• consensus

  /consensus Command - Multi-Agent Consensus Review

• conversation-history-sparse

  Sparse conversation history triage across Claude Code, Codex, Hermes, agy CLI, and Cursor with strict context budgets. Default for `/history`; covers all five canonical sources.

• copilot-pr-processing

  Use when /copilot is requested to triage and process pull-request review comments.

• crash

  Canonical triage order for crash investigation reports to surface panic traces, rank variables, and propose next steps.

• credential-discipline

  Example/seed/fixture files must use placeholders not real credentials. Pre-commit grep check + enforcement hooks.

• cross-machine-ssh-tier

  Reusable SSH-first-then-Tailscale transport ladder for reaching peer machines. Tier 1 is LAN SSH via a `~/.ssh/config` alias; Tier 2 is Tailscale SSH with explicit `-i ~/.ssh/id_<peer>` key, looked up live (never hardcoded); Tier 3 is a Slack channel watched by a reactive messaging-gateway agent, fo

• cwd-safety

  Use BEFORE `mv`/`rm -rf` on any directory. Verifies pwd does not match target; session cwd cannot recover once its directory is gone.

• 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 CXDB, and the Healer clusters failures in

• deletion-milestone

  Generic discipline for any deletion or quarantine milestone PR — net LOC enforcement, scope verification, PR lifecycle guards

• design-doc

  Generate comprehensive product spec, engineering design, and TDD implementation plan documents for any feature or project. Consolidated 2026-07-11 from the retired /design command (whose newer Phase-0 exit-criteria-first + batch-decision contract is authoritative — see the AUTHORITATIVE ENTRY CONTRA

• design

  Generate HTML + MD design docs for a feature or PR, matching the repo's existing design doc style. Always produces both formats in parallel.

• dice-roll-audit

  Audit campaign dice rolls for fairness, anomalies, mechanics validation, and evidence.

• disk-audit

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

• disk-magician

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

• disk-root-cause

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

• distributed-caching

  Distributed system and caching architecture rules before adding any cache, memo, or in-memory store.

• document-standards

  Project-agnostic review or revision of prose documents (roadmap docs, reports, status docs, handoffs, Google Docs, HTML) for truth, economy, readability, structure, and output correctness — optimized for human reading. Adapts /code-standards' five-lane pattern to documents. Dispatched by the /docume

• docx

  Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterhea

• domain-lock-standards

  Standard operating procedure for AI coding agents when encountering spawn-time or real-time domain lock collisions.

• draft-first-pr

  Lifecycle contract for opening PRs, driving them green, and fixing CI. Triggers on: opening a PR, driving a PR to green, fixing CI on a PR, /green, /es, /er, /advice on a PR.

• end2end-testing

  Use when adding or modifying end-to-end tests, testing provider-backed application flows, choosing realistic fixtures, or debugging integration failures across service boundaries.

• engplan

  Plan medium-to-large engineering work across staged PRs with file ownership, dependencies, tracking, and proportional evidence.

• evidence-coverage

  Build a Logic x Evidence Matrix mapping every production logic change in a PR to its required testing layer and current evidence status.

• evidence-review

  Enforcement rules for reviewing evidence artifacts against the evidence-standards skill. Invoked by /er. Produces PASS / PARTIAL / FAIL / INCONCLUSIVE verdicts.

• evidence-standards

  General cross-project evidence standards (user scope). Use for the /es skill. Repo-level .claude/skills/evidence-standards.md files add project-specific extensions — always consult both.

• execute

  Use when /execute is requested to plan, confirm authorized scope, and execute work.

• execution-orchestration

  Use when /e is requested for explicit planning and cost-aware task execution.

• experiment

  Triple-blind AI testing protocol for scientifically rigorous experiments that test AI behavior changes (e.g. CLAUDE.md variants, prompt strategies) while eliminating coordinator and evaluator bias. Use when the user wants to run /experiment, design a controlled A/B test of AI behavior, compare contr

• ezgha-watchdog

  Read-only fleet-size consumer for the 6 mac + 16 linux ezgha runner invariant. Restart-only remediation is UNAVAILABLE (fail-closed) pending jleechanorg/ez-gh-actions PR 67 (dual-Lima convergence) and PR 70/issue 60 (recovery controller) merging AND being proven live-deployed — a 2026-07-09..11 audi

• factory-evolve

  Analyze conversation and git history to find gaps where cold reviews (codex, Bugbot, CodeRabbit, /reviewdeep) caught issues that dark-factory in-pipeline reviewer nodes missed. Fans out subagents, opens PRs, drives each through /green, and merges (with explicit MERGE APPROVED). Proposes targeted .do

• factory-spec
• fetch-x-tweet
• field-ownership-contracts
• file-justification
• firebase-prod-campaigns
• fix-completion-deploy
• fixpr
• frontend-design
• game-evidence-reviewer
• gemini-3-api
• gemini-code-execution-json-mode
• generalized-testing
• generatetest
• git-branch-tracking
• github-actions-policy
• github-cli-reference
• gmail
• goalexec-define
• goalexec
• harness-engineering
• harness-guardrails
• harness-postmortem
• hermes-models
• hermes-slack-rotation
• history-search
• host-disk-guardian
• innovation
• integrate
• integration-verification
• ironclad
• isolate-llm-vs-backend
• karpathy-wiki
• keychain-kill
• launchd-plist-template
• launchd
• learn
• level-up-validation
• levelup
• linux-mirror
• linux-remote
• llm-first
• llm-prompt-engineering
• llm-testing
• local-dev-server
• mac-mirror
• mac-remote
• mcp-agent-mail
• mcp-builder
• mem0
• memory-search
• minimax-401-diagnostic
• minimax
• mobile-investigations
• nextsteps
• no-second-llm-calls
• orchconverge
• org-runner-audit
• pair-benchmark-all-executors
• parallelize-to-ceiling
• pdf
• plan-micro
• playwright-ui-testing
• ponytail
• pptx
• pr-babysit
• pr-blocker-min-repro
• pr-description-format
• pr-description-sections
• pr-driver-protocol
• pr-efficiency-audit
• pr-green-definition
• pr-preview-servers
• pr-quantity-control
• pr-report
• pr-workflow-manager
• pre-cr-checklist
• readonly-scope
• ready
• redgreen
• repo-and-infra-locations
• repro-copy
• repro-developer
• repro-evidence
• repro-twin-clone-evidence
• repro
• research
• reviewer-calibration
• roadmap
• root-cause-first
• runner-health
• runtime-activation-claim
• second-call-boundary
• secondo-dependencies
• self-hosted-runner-preflight
• session-start-protocol
• sidekick
• skillify
• slack-audit
• slack-identity
• slack-media-upload
• slash-command-translation
• smoke-local
• smoke-test-local
• smoke
• soak
• social-poster
• streaming-evidence-standards
• superpowers-brainstorming
• superpowers-quick
• superpowers-using-git-worktrees
• superpowers-verification-before-completion
• superpowers-writing-plans
• swarm
• sync-live-config
• sync
• systemd
• tdd-evidence-workflow
• test-classification
• test-realistic
• testing-gap-close
• testing-infrastructure

Similar plugins