Reads raw `.agents/` artifacts and compiles them into a structured, interlinked

> **Quick Ref:** Execute every open issue in an epic via wave-based workers using `spawn_agent`, `wait_agent`, `send_input`, and `close_agent`. Output: closed issues + final validation.

> **Quick Ref:** One command, full lifecycle. `$discovery` → `$crank` → `$validation`. Thin wrapper that delegates to phase orchestrators.

Source of truth: `docs/contracts/codex-skill-api.md`

Spawn isolated agents to execute tasks in parallel with Codex session agents. Fresh context per agent.

> **Quick Ref:** One command to set up the full AgentOps product layer. Progressive — bare repos get everything, existing repos fill gaps only.

> **Quick Ref:** 4-phase investigation (Root Cause → Pattern → Hypothesis → Fix). Output: `.agents/research/YYYY-MM-DD-bug-*.md`

> **Quick Ref:** Autonomous epic execution. `/swarm` for each wave with runtime-native spawning. Output: closed issues + phase-2 handoff for `/validation`.

> Quick Ref: `/deps audit` | `/deps update [--major|--minor|--patch]` | `/deps vuln` | `/deps license`

> **Quick Ref:** Validates that a proposed goal aligns with the product's strategic direction before discovery begins major work. Council-gated with `--preset=product`.

**YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it.**

'Create structured handoff for session continuation. Triggers: handoff, pause, save context, end session, pick up later, continue later.'

> **Purpose:** Detect and auto-fix common skill hygiene issues across the skills/ directory.

> **Quick Ref:** Execute single issue end-to-end. Output: code changes + commit + closed issue.

> **Quick Ref:** Decompose goal into trackable issues with waves. Output: `.agents/plans/*.md` + bd issues.

Trace knowledge artifact lineage to sources.

> **One job:** Tell a new user what AgentOps does and what to do first. Fast.

'Deep codebase exploration. Triggers: research, explore, investigate, understand, deep dive, current state.'

Author and manage holdout scenarios for behavioral validation. Scenarios are stored outside the codebase in .agents/holdout/ where implementing agents cannot see them. Triggers: scenario, holdout, behavioral scenario, create scenario, list scenarios.

> **Purpose:** Run repeatable security checks across code, scripts, hooks, and release gates.

Spawn isolated agents to execute tasks in parallel. Fresh context per agent (Ralph Wiggum pattern).

> **Quick Ref:** Trace design decisions through CASS sessions, handoffs, git, and artifacts. Output: `.agents/research/YYYY-MM-DD-trace-*.md`

> **Purpose:** Is this code ready to ship?

Concrete tool calls for spawning agents using Codex CLI (`codex exec`). Used for `--mixed` mode cross-vendor consensus and as the primary backend when running inside a Codex session with `spawn_agent`

Draft Diversity, Equity, and Inclusion statements for academic applications.

> **Source**: [https://github.com/aipoch/medical-research-skills](https://github.com/aipoch/medical-research-skills)

Access ENCORI (StarBase) database for miRNA-target, RNA-RNA, and other regulatory data. Invoke when user asks to search ENCORI or retrieve regulatory interactions.

Search FDA industry guidelines by therapeutic area or topic.

NIH funding trend analysis to identify high-priority research areas.

A Pythonic wrapper around RDKit with simplified interfaces and sensible defaults. Preferred for standard drug discovery workflows including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformer generation, and parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.

> **Source**: [https://github.com/aipoch/medical-research-skills](https://github.com/aipoch/medical-research-skills)

'Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to official OpenAI domains.'

'Investigate bugs or audit code with repro evidence, root cause analysis, and fixes.'

'Audit, update, and validate dependencies, vulnerabilities, and licenses.'

'Validate product fit before discovery using PRODUCT.md and scope checks.'

'Orchestrate brainstorm, research, plan, and pre-mortem into an execution packet.'

'Create compact session handoffs for continuation after pause or compaction.'

'Repair skill hygiene: frontmatter, links, references, manifests, and parity drift.'

'Build an external-knowledge wiki from clipped articles, papers, and transcripts.'

'Use official OpenAI docs for API/product questions needing current citations.'

'Decompose goals into issue-ready plans, waves, dependencies, and validation checks.'

'Trace where knowledge, decisions, or artifacts came from.'

'Detect AgentOps setup and give one concise next action.'

'Explore a codebase or question and write evidence-backed findings.'

'Run repository security scans and release-gating checks.'

'Shared reference contracts used by other AgentOps skills.'

'Trace decisions and concepts through history, artifacts, and git.'

'Run full lifecycle: discovery, crank implementation, validation, and report.'

Use the `wtx` PowerShell CLI to create, navigate, and manage git worktrees for parallel development in this monorepo.

This provides essential guidance for AI coding agents working on this repository.