ImL1s

ImL1s/resume-skills

Instructions file CodexOpenCode

Instructions for ImL1s/resume-skills, covering agent notes — portable-resume-skills, product, verify before claiming done, honesty gates and fixtures.

ImL1s/GUI-Anything

Plugin Claude Code

Plugin marketplace listing 1 plugin: gui-anything.

ImL1s/GUI-Anything

Skill Claude CodeCodex

Use when the user wants Codex to build, refine, test, or validate a GUI-Anything harness for any software or source repository. Adapts the GUI-Anything methodology to Codex without changing the generated React+Tauri harness format.

ImL1s/GUI-Anything

Plugin Claude Code

Build cross-platform GUI interfaces for any software using the gui-anything harness methodology.

ImL1s/GUI-Anything

Command

Build a complete GUI harness for any software application.

ImL1s/GUI-Anything

Command

List all GUI-Anything harnesses in the current repository.

ImL1s/GUI-Anything

Command

Expand and improve an existing GUI harness with additional coverage.

ImL1s/GUI-Anything

Command

Run tests for a GUI harness and update TEST.md with results.

ImL1s/GUI-Anything

Command

Validate a GUI harness against HARNESS.md standards and best practices.

ImL1s/charge-pilot

Instructions file CodexOpenCode

AGENTS.md instructions for ImL1s/charge-pilot, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

ImL1s/agent-cli-skills

Plugin Claude Code

Plugin marketplace listing 1 plugin: agent-cli-skills.

ImL1s/agent-cli-skills

Plugin Claude Code

Headless Agent Skills wrappers for agy, Grok, Claude Code, Codex, Kimi, Qwen, plus multi-cli-spawn (PID-safe council with .status wait contract).

ImL1s/agent-cli-skills

Skill Claude CodeCodex

Run Google Antigravity CLI (agy) headlessly via agy-exec.sh / agy-task.sh / agy-explore.sh. Use when the user asks for agy, Antigravity, Gemini CLI agent, or to execute a plan with agy. Always allocates a PTY (agy -p is silent without TTY). Prefer -f for long prompts; --no-git and orchestrator-owned commits. -r…

ImL1s/agent-cli-skills

Skill Claude CodeCodex

Run Anthropic Claude Code headlessly via claude-exec.sh (claude -p). Use when the user asks for Claude Code, claude CLI, ultracode, Claude workflows, agent teams, or Claude subagents. -r is plan mode (clears skip-permissions); -T/--ultracode enables effort ultracode + multi-agent preamble; -P sets permission-mode.…

ImL1s/agent-cli-skills

Skill Claude CodeCodex

Run OpenAI Codex CLI headlessly via codex-exec.sh (codex exec). Use when the user asks for Codex, GPT coding agent, codex exec, Codex subagents, or spawnagentsoncsv. -r / read-only sandbox blocks workspace writes — use -s workspace-write when the prompt must write files. -T prefers subagents. Orchestrator owns git…

ImL1s/agent-cli-skills

Skill Claude CodeCodex

Run xAI Grok Build CLI headlessly via grok-exec.sh. Use when the user asks for grok, Grok Build, xAI coding agent, spawnsubagent, or grok worktrees. -r is plan mode with write/shell denied; -T asks for native subagent fan-out; -w enables --worktree. No PTY required. Orchestrator owns git.

ImL1s/agent-cli-skills

Skill Claude CodeCodex

Run Moonshot Kimi Code CLI headlessly via kimi-exec.sh. Use when the user asks for kimi, Kimi Code, Moonshot coding agent, or kimi agent profiles (--agent / --agent-file). -r is a soft read-only prompt guard; -p auto-approves tools. On 403 usage limit mark BLOCKED — do not retry-loop. Orchestrator owns git (--no-git).

ImL1s/agent-cli-skills

Skill Claude CodeCodex

Fan out one brief to multiple coding CLIs in parallel (agy, grok, claude, codex, kimi, qwen) via spawn.sh with PID-file / process-group kill safety and per-seat .status files (RUNNING → DONE|BLOCKED). Use for multi-LLM council, parallel second opinions, or cross-provider review. Prefer foreground wait; for --no-wait…

ImL1s/agent-cli-skills

Skill Claude CodeCodex

Run Alibaba Qwen Code CLI headlessly via qwen-exec.sh. Use when the user asks for qwen, Qwen Code, or qwen review / Agent-tool subagents. -r enables sandbox + read-only guard; -T asks for Agent tool / configured subagents. On 429/quota mark BLOCKED — do not retry-loop. Orchestrator owns git (--no-git).

ImL1s/agent-game-engine

MCP server Claude CodeCodexCursor +2

MCP server "agent-game-engine" as configured in ImL1s/agent-game-engine. Runs locally from the agent-game-engine npm package.