메뉴
Use when exploring has locked CONTEXT.md and the work needs planning before validation.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when the user asks to create a persistent repo-local Codex agent, scaffold `.codex/agents/*.toml`, define a reusable specialist role, or match an agent to existing local skills and MCP servers.
Use when designing or implementing a premium animated landing page with AI-generated visuals or looping video, especially when the workflow involves Higgfield-style image and video generation, Google AI Studio-style code prompting, React or Tailwind landing-page implementation, dark-mode video blending, scroll-tied playback, aspect-ratio-matched media blocks, or motion-first section design.
Use when the user asks to fine-tune on books, create an SFT dataset from books, train a style-transfer or author-voice model, extract ePub text, segment long-form book content, or prepare literary data for LoRA or small-model training.
Bootstrap a new AI-agent session by reading the repository operating docs and rebuilding project understanding from source. Use when Codex needs to start a new conversation, get up to speed on an unfamiliar repo, read AGENTS.md and README.md completely before acting, investigate the codebase to understand the project's purpose and architecture, or turn a rough onboarding prompt into an execution-ready repo-orientation prompt.
Use when reviewing completes or work is intentionally abandoned. Extract durable patterns, decisions, and failures into history/learnings, then promote only critical reusable lessons to critical-patterns.md.
Use when Codex should turn a concept, topic, tutorial, lesson, algorithm, system, workflow, or abstract idea into a playable browser game that teaches through interaction. Use for planning or implementing educational web games with the Game Studio plugin, including concept-to-mechanic translation, gameplay loop design, learning progression, and browser-game QA.
| name | planning |
| description | Use when exploring has locked CONTEXT.md and the work needs planning before validation. |
| metadata | {"ecosystem":"khuym","dependencies":{"beads-cli":{"kind":"command","command":"br","missing_effect":"unavailable","reason":"Planning creates and links real bead graphs with br."},"beads-viewer":{"kind":"command","command":"bv","missing_effect":"degraded","reason":"Planning relies on graph-aware triage and validation checks."},"cass-cli":{"kind":"command","command":"cass","missing_effect":"degraded","reason":"Planning searches prior sessions to avoid re-solving problems."},"cass-memory":{"kind":"command","command":"cm","missing_effect":"degraded","reason":"Planning retrieves reusable playbook context before deep work."},"gkg":{"kind":"mcp_server","server_names":["gkg"],"config_sources":["repo_codex_config","global_codex_config","plugin_mcp_manifest"],"missing_effect":"degraded","reason":"Discovery architecture snapshots rely on gkg-backed analysis."}}} |
Planning turns locked CONTEXT.md decisions into the smallest believable path to execution. Tough work uses capability/risk epics and a current story for feasibility validation.
If .khuym/onboarding.json is missing or stale, stop and invoke khuym:using-khuym.
CONTEXT.md is source of truth.node .codex/khuym_status.mjs --json when available.Epic Map -> Current Story Pack over forced 2-4 phases.khuym:validating.Mode -> Shape -> Epic Map? -> Current Story Pack -> Beads.
Phase = optional milestone; epic = capability/risk area; story = end-to-end outcome; bead = worker task for validated work.
Load references/planning-reference.md for quality rules and artifact templates.
CONTEXT.md, read learnings.approach.md with path, risks, proof needs, files, and validating questions.khuym:validating.Planning has chosen the smallest work shape. Approve it before current story/work prep. Tough work uses an epic map; beads wait until feasibility passes.
CONTEXT.md