agentic-workflows instructions

romarayt/raytsystem-public-os

Agent

Instructions for creating skills, agents, and packs: reusable definitions that extend a coding agent's behavior.

romarayt/raytsystem-public-os

Agent

An overview of raytsystem's catalogue of extensions, including agents, skills, packs, instructions, and runtime adapters. It explains where these definitions come from and how their origin and permissions are checked.

romarayt/raytsystem-public-os

Agent

A controlled set of eight typed video-processing tools for handling video, audio, transcripts, and frames. It uses fixed input and output contracts, local staging, provenance records, timeouts, file limits, and approval rules.

appautomaton/agent-designer

Instructions file CodexOpenCode

AGENTS.md instructions for appautomaton/agent-designer, covering agents, priorities, tooling and tests, safety and output style.

appautomaton/agent-designer

Skill Claude CodeCodex

Delegate tasks to Google's Antigravity CLI (agy) for prototyping, debugging, code review, and research. Supports multi-turn sessions via SESSIONID. Successor to the retired Gemini CLI.

appautomaton/agent-designer

Skill Claude CodeCodex

Delegate tasks to Claude Code CLI for prototyping, debugging, and code review. Supports multi-turn sessions via SESSIONID.

appautomaton/agent-designer

Skill Claude CodeCodex

Delegate tasks to Codex CLI for prototyping, debugging, code review, implementation handoff, cross-model second opinions, and multi-turn Codex sessions via SESSIONID.

AlexZio00/sovereign-skills

Plugin Claude Code

Carves safety-adjacent requests into a safe scope, executed by a genuinely isolated fresh-context subagent, with an adversarial verify pass and a descope ledger.

AlexZio00/sovereign-skills

Skill Claude CodeCodex

🔬 CODE AUTOPSY v7.2 "12 Questions + Quantified + Deployment Verdict + diff mode + CRITICAL hard cap + Factuality Gate".

AlexZio00/sovereign-skills

Plugin Claude Code

13-section AI collaboration audit — analyzes actual work patterns (not surveys) to generate behavioral profile, blind spots, and growth direction.

AlexZio00/sovereign-skills

Skill Claude CodeCodex

This skill should be used when the user types /collab-audit or requests AI collaboration diagnosis. Analyzes conversation history, artifacts, and work patterns to generate a 14-section AI Collaboration Audit. Behavioral analysis and feedback are bundled by design — separating them causes users to skip one, defeating…

AlexZio00/sovereign-skills

Skill Claude CodeCodex

Agent Discipline Engine — lock the goal, run PLAN→DO→VERIFY→FINALIZE→OUTPUT loop, detect success masquerading. Triggers: '/goal-lock', '/goal-lock quick', 'goal lock', 'task harness'.

XhinLiang/awsl

Skill Claude CodeCodex

Run Claude Code JavaScript Workflows through the awsl compatibility runtime. Use when an agent's current task or loaded Skill requires dispatching a Claude Code Workflow but the host cannot execute that Workflow natively, or when awsl workflow inspection, durable run state, resume, or provider diagnostics are needed.

jcarlosrodicio/opencode-agent-orchestration-kit

Agent

Main product-development orchestrator for research, design, spec, implementation, and review.

jcarlosrodicio/opencode-agent-orchestration-kit

Agent

Coordinates deterministic review preparation and explicit partial AI review modes.

jcarlosrodicio/opencode-agent-orchestration-kit

Agent

Final code-review authority. Audits the real diff, safety, architecture, evidence, and task compliance without editing files.

jcarlosrodicio/opencode-agent-orchestration-kit

Command

Run a bounded, locally verifiable autonomous engineering workflow.

jcarlosrodicio/opencode-agent-orchestration-kit

Command

Run an optional AHE iteration to evaluate or improve this OpenCode harness with evidence and attribution.

jcarlosrodicio/opencode-agent-orchestration-kit

Command

Design and run a bounded engineering loop with durable state, human approval, and independent verification.

jcarlosrodicio/opencode-agent-orchestration-kit

Skill Claude CodeCodex

Patterns and architectures for autonomous loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems. Use when setting up autonomous development workflows, choosing the right loop architecture, or building CI/CD-style continuous development pipelines.

jcarlosrodicio/opencode-agent-orchestration-kit

Skill Claude CodeCodex

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

jcarlosrodicio/opencode-agent-orchestration-kit

Skill Claude CodeCodex

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now…

vincentkoc/dotskills

Plugin Claude Code

Plugin marketplace listing 20 plugins: codebase-memory-mcp, codex-goal-mining, codex-session-recovery, crabpot-perf-metrics, crawlkit.

vincentkoc/dotskills

Instructions file CodexOpenCode

Instructions for vincentkoc/dotskills, covering agents.md, repository purpose, mandatory contribution flow, skill standards and openai metadata defaults.