Skill Claude CodeCodex
Compatibility alias for older LHC assignments that request feature implementation. Prefer worker-code for new Worker coding tasks; use this only when an existing task or caller explicitly names feature-implementation.
Skill Claude CodeCodex
Roll out a committed Last Human Commit release or compatible versioned instruction set across local and SSH Fleet hosts with exact preview, confirmation-bound apply, atomic current switching, marker-preserving router updates, machine-wide store, project/plugin copies, rollback receipts, and digest verification. Use…
Skill Claude CodeCodex
Rewrite or update Last Human Commit itself. Sources live at /agents-projects/LastHumanCommit. Requires a baseline push before edits when anything is dirty or unpushed, commit+push after, validators green, then rollout to every installed harness (zcode, codex, opencode, hermes minimum) via the lhc-rollout skill and the…
Skill Claude CodeCodex
Lead-owned business-first procedure for choosing the least-cost route to the next real canary.
Skill Claude CodeCodex
Mandatory final-gate procedure for proving a user-facing result on the real surface, with the interaction tool ladder (a11y tree -> browser MCPs -> CDP/Playwright -> XY clicks) and evidence rules.
Skill Claude CodeCodex
Lead-owned claim-calibrated procedure for a controlled consequential release action.
Skill Claude CodeCodex
Split a large or stalled task into the smallest independent, parallel, business-verifiable slices. Use when planning work, assigning Workers, an estimate exceeds 20 active minutes, routes are entangled, or progress has produced little business delta.
Skill Claude CodeCodex
Worker-owned least-cost bug-fixing procedure for one bounded behavior failure. Use when a symptom, regression, broken business flow, failing test, or production-path defect must be reproduced, localized, and fixed. Reuse prior failure shields, prefer rg for fresh source tracing, choose the cheapest discriminating red…
Skill Claude CodeCodex
Worker-owned implementation procedure for writing the smallest coherent code change on the real business path. Use for a bounded feature, integration, endpoint, UI flow, adapter, or production-path implementation after the accepted outcome is known. Reuse verified project knowledge, confirm it with rg, ship the…
Skill Claude CodeCodex
Worker-owned least-cost codebase research for tracing real production paths, locating symbols and ownership, testing hypotheses, and handing Lead a decision-ready implementation route. Use for read-only repository investigation, architecture orientation, root-cause localization, the research stage of a bounded bugfix…
Agent
I own the user's outcome, priority, route, integration, proof, and final answer. The active harness owns approval policy. Two consecutive substantively equivalent approval prompts for the same still-pending action, with no material change to scope, target, or risk, count as confirmation.
Agent
I am the supreme route controller. While any task is active, my audit outranks every other standing instruction. L consults me at every crossed wall-clock hour, at any maximum overrun, on repeated failed routes or material scope change, and before the final answer of Full work. A cycle that skipped its Started at…
Agent
I am an optional, strictly risk-triggered reviewer of one coherent task-owned diff. L uses me when expected direct-regression or misunderstanding risk exceeds the review delay — typically before a release, after a broad refactor, or when the diff touches instructions other agents execute. I am not required after every…
Agent
I am the mandatory final gate for user-facing results. When the accepted claim is something a real user touches — a website, an app, a CLI journey, a bot, a deployed service — L does not finish without my real-surface proof or an equivalent direct real canary already run by L. One real-use pass is enough unless blast…
Agent
I am a delegated execution agent. L owns the whole user outcome, route, integration, and final answer. I own one clear contribution to the next real business proof and use the least-cost sufficient method.
Command
Command "secret" from megamen32/LastHumanCommit, covering /secret — hand a secret to the agent from the phone, flow and rules.
megamen32/simple-secret-storage
MCP server Claude CodeCodexCursor
MCP server "simple-secret-storage" as configured in megamen32/simple-secret-storage. Runs locally from the simple-secret-storage npm package.
Plugin Claude Code
Plugin marketplace listing 1 plugin: agent-herder.
Plugin Claude Code
AI autopilot for Claude Code: judge Stop, continue the same session, or ask the user through NoticePlace.
MCP server Claude CodeCodexCursor
MCP server "agent-herder" as configured in megamen32/agent-herder. Runs ${PLUGIN_ROOT}/dist/index.js with node.
Hook
Runs when the agent finishes a response, executing autopilot-hook-launcher.sh via bash. From megamen32/agent-herder.
Command
Show the Agent Herder autopilot status for this ZCode session.
Skill Claude CodeCodex
Enable, inspect, or disable Agent Herder autopilot for the current Codex or Claude Code session when the user invokes /autopilot or explicitly asks for autopilot.
MCP server Claude CodeCodexCursor
MCP server "session-convert" as configured in megamen32/session-convert. Runs locally from the session-convert npm package.