agentic-coding commands

stereosam/stereo-vibe-public

Command

A command that registers a new project in a shared memory file, assigning it the next free number and optionally recording its description and folder.

Master0fFate/parallax-claudecode

Command

Part of parallax-claudecode

Summarize the current session and run package/native lifecycle diagnostics.

jubayertalha/vibeframe

Command

Part of vibeframe

Plan and implement a feature through the VibeFrame model (context → declare → implement → link → validate).

jubayertalha/vibeframe

Command

Part of vibeframe

Explain unmapped code changes and fold them into the VibeFrame model.

jubayertalha/vibeframe

Command

Part of vibeframe

Walk the VibeFrame drift inbox and resolve each finding (fix / accept / dismiss).

avelikiy/great_cto

Command

HR-AI / AEDT bias audit. Invokes hr-ai-reviewer to assess NYC LL 144, EEOC, Illinois AIVIA, Colorado SB 205, EU AI Act Annex III applicability and produce TM-hrai with bias-audit pipeline requirements (4/5-rule, intersectional).

avelikiy/great_cto

Command

Gracefully retire an LLM agent from the workforce. Archives prompt, removes from sync list, keeps verdicts for audit. Like firing a human — but reversible.

avelikiy/great_cto

Command

Performance review for an LLM agent (or all agents). Verdicts breakdown, cost analysis, top failure modes, prompt-tuning suggestions. Like a human '1:1' but for AI workforce.

spacehendrix/clauder

Command Claude Code

Use the "consult7" MCP server to request help from "openai/gpt-5", or the model explicitly specified, regarding the following request. Send it the following request, along with the relevant codebase, ALWAYS EXCLUDING all files and folders described in .claudeignore and .gitignore, as well as any file for which the…

spacehendrix/clauder

Command Claude Code

For this task only, act as a Claude sub-agent expert providing recommendations for what new Claude sub-agents are relevant to add to the project, or to satisfy the user's intent should they have provided one. You understand that sub-agents have their own context and are not aware of what other sub-agents are doing, or…

ldilov/harness-forge

Command

Use when an agent should inspect the current Harness Forge workspace state before acting.

ldilov/harness-forge

Command

Use when an agent should inspect Harness Forge task-runtime folders, task packs, and linked artifacts for the current work item.

ldilov/harness-forge

Command

Use when an agent should preview or apply a non-destructive Harness Forge package refresh while preserving gathered runtime state.

ldilov/harness-forge

Command

Use when a task needs structure, sequencing, risks, and validation checkpoints.

ldilov/harness-forge

Command

Use when defining or running verification for code, docs, templates, or migration work.

niels-emmer/myace

Command

Read-only cross-check of spec, plan, and tasks for consistency, duplication, gaps, and constitution violations before implementation starts.

niels-emmer/myace

Command

Systematically find and resolve the highest-impact ambiguities in a spec before planning starts, instead of discovering them mid-implementation.

niels-emmer/myace

Command

Create or update the project's constitution — the small set of non-negotiable product/architecture principles every spec, plan, and implementation must be checked against.

niels-emmer/myace

Command

Execute a task list in dependency order, tests before implementation for each task, halting on any non-parallel failure instead of pressing ahead.

niels-emmer/myace

Command

Turn a clarified spec into a concrete technical plan — architecture, data model, and interfaces — before any task breakdown or code.

niels-emmer/myace

Command

Turn a short feature request into a written spec — user-facing behavior and testable acceptance criteria, deliberately free of implementation detail — before any planning starts.

niels-emmer/myace

Command

Turn a plan into an ordered, independently-checkable task list, with every task traceable back to a requirement and every requirement covered by at least one task.

niels-emmer/myace

Command

Pre-deployment evaluation checklist — holdout eval, baseline comparison, leakage scan, failure mode documentation.

niels-emmer/myace

Command

Scaffold a new tracked experiment — create notebook, set up tracking, log baseline, define success criteria.