Command Codex
Audit DESIGN.md against the actual code. Writes DESIGN.md.critique.md adjacent to DESIGN.md with five audit passes structural / drift / accessibility / completeness / consistency. Each finding has a stable id and a /mddesign:fix suggestion.
Command Codex
Deep diagnostic. Checks every MDDesign dependency, verifies hooks fire, validates the lint toolchain, tests scratch directory write, and prints a fix-it for every failure. Use when something is broken or before publishing to confirm a clean install.
Command Codex
Apply a single safe quick win from DESIGN.md.critique.md. HITL gated. Re-lints DESIGN.md after every edit; reverts if lint regresses.
Command Codex
Force a session catchup or a memory promotion outside the hook lifecycle. Default is catchup (read-only); promote is HITL gated.
Command Codex
Scan the current codebase, cluster de-facto design tokens, write a structurally valid DESIGN.md at project root. Uses the design-archeologist subagent for the scan. Validates with npx @google/design.md lint and iterates until valid.
Command Codex
Manual one-shot inject of relevant DESIGN.md tokens into the current phase's findings.md "## Design Context" section. Useful before starting a UI subtask.
Command Codex
Save or recall via the three-tier memory layer. Routes to scratch (file-tier), WHERE (QMD via code-memory-router), or WHY (MemPalace via code-memory-router). Every WHY-tier write goes through the HITL gate.
Command Codex
Walk the user through installing every MDDesign dependency. Detects what is missing, prints exact install commands for the current platform, and verifies after each step. Safe to run multiple times.
Command Codex
Dispatch a phase to a specialist subagent via PhaseSpec v1. Auto-picks the subagent if not specified. HITL gated before dispatch. Result appended to progress.md under "Phase Result".
Instructions file CodexOpenCode
Instructions for OthmanAdi/MDDesign, covering agents.md — mddesign, what mddesign is, what mddesign is not, files in a project that uses mddesign and hook lifecycle.
Instructions file
Instructions for OthmanAdi/MDDesign: See AGENTS.md. Same content; Claude Code reads this file natively, agents that read AGENTS.md get the same orientation there.
Instructions file Gemini CLI
Instructions for OthmanAdi/MDDesign: See AGENTS.md. Same content; Gemini CLI reads this file natively.
Hook
Runs when a session starts on startup, clear and compact, executing preamble.ps1. From OthmanAdi/MDDesign.
Hook
Runs when you submit a prompt, before the agent sees it, executing enforce.ps1. From OthmanAdi/MDDesign.
Hook
Runs before the agent uses a tool for Write and Edit tool calls, executing gate.ps1. From OthmanAdi/MDDesign.
Hook
Runs when the agent finishes a response, executing promote.ps1. From OthmanAdi/MDDesign.
OthmanAdi/open-responses-agent-skill
Plugin Claude Code
Build autonomous agents in Rust, TypeScript, or Python using Open Responses API for seamless multi-provider support (OpenAI, Anthropic, HuggingFace, etc.).
OthmanAdi/open-responses-agent-skill
Cursor rule Cursor
Open Responses Agent Development - Build autonomous agents with the unified HuggingFace router.
OthmanAdi/open-responses-agent-skill
Instructions file CodexOpenCode
Instructions for OthmanAdi/open-responses-agent-skill, covering open responses agent development, about this skill, core knowledge, single unified endpoint and provider selection via model suffix.
OthmanAdi/open-responses-agent-skill
Skill Claude CodeCodex
Build autonomous agents using Open Responses API via HuggingFace Inference Providers. Single unified endpoint with multi-provider routing via model suffixes. Use the OpenAI SDK with custom baseurl for seamless development.
Cursor rule Cursor
Time-awareness for coding agents. Consult shell clock + file mtimes before reasoning about "when" or "how long ago". No hooks on Cursor — degraded mode only.
Instructions file CodexOpenCode
Instructions for OthmanAdi/chronos, covering chronos — time awareness (agents.md mirror), you have a ledger (or you don't), 7 triggers — when to consult time, read the ledger and last 10 min of events.
Skill Claude CodeCodex
Gives AI coding agents temporal awareness via a hook-backed ledger and decision rules. Activates whenever an agent reasons about recency, retry windows, memory staleness, deploy cooldowns, idle detection, or any "when / how long ago" question. Required for autonomous or long-running agents.
Skill Claude CodeCodex
Decompose features from an existing codebase into detailed, agent-ready specifications for replatforming or migration. Use when analyzing legacy code, extracting feature behavior, mapping old architecture to new, or preparing migration specs. Triggers on keywords like decompose, analyze features, extract behavior…