원클릭으로 Manus에서 모든 스킬 실행

harness-planner

스타1

포크1

업데이트2026년 6월 21일 18:56

Generic exhaustive planner support. Produces/maintains horizon slice from vision + categories using Ruflo for state and optional sub-agents. Called conceptually from orchestrator procedure. Decoupled: loads project files only.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

arvindrk

arvindrk/ycagent.ai

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

SKILL.md

readonly

name	harness-planner
description	Generic exhaustive planner support. Produces/maintains horizon slice from vision + categories using Ruflo for state and optional sub-agents. Called conceptually from orchestrator procedure. Decoupled: loads project files only.

Load vision.md, categories.json, current horizon (Ruflo "harness:horizon" or agent/harness/horizon.json), feature_list, PROGRESS.
Use memory_search for past decisions on vision/horizon/balance.
If needed, propose horizon update (use agent_spawn for sub-agents e.g. vision-align, category-balance, lookahead-decompose when complex):
- Map tasks to vision goals.
- Score proposed next 3-5 for category distribution (weights + no excessive repeats across slice/recent).
- Respect depends_on and unblocked.
Persist horizon slice + mix summary to Ruflo memory (and optionally file).
Return the immediate next item + rationale (vision link, category contribution).
Record any planning notes to PROGRESS (or let main flow do it).

The main orchestrator prompt sequences this before execution. Sub-agents (via Ruflo spawn) can be used for individual steps above when the lookahead is complex.

This skill + vision/categories/horizon make the planner extensible, scalable (sub-agents + memory), and decoupled from repo business logic. Harness core never embeds domain prefs.

이 저장소의 다른 Skills

같은 저장소

feature-planning

arvindrk/ycagent.ai

Generic planner for feature work using agent/feature_list.json + vision/categories. Use after merges, roadmap changes, or failed verification. Load project vision.md and categories.json for direction and balance.

2026-06-211

codex-pr-review

arvindrk/ycagent.ai

Review ycagent.ai changes before creating a draft PR. Use after code or config changes and before pushing a branch.

2026-06-191

repo-bootstrap

arvindrk/ycagent.ai

Re-enter ycagent.ai agent work. Use at the start of any Codex session, automation, or resumed thread in this repo.

2026-06-191

ycagent-research-eval

arvindrk/ycagent.ai

Design and run lightweight evals for the YC company research agent. Use when changing Trigger.dev tasks, E2B browsing, LLM providers, source crawling, extraction, or synthesis.

2026-06-191

name	harness-planner
description	Generic exhaustive planner support. Produces/maintains horizon slice from vision + categories using Ruflo for state and optional sub-agents. Called conceptually from orchestrator procedure. Decoupled: loads project files only.

Load vision.md, categories.json, current horizon (Ruflo "harness:horizon" or agent/harness/horizon.json), feature_list, PROGRESS.
Use memory_search for past decisions on vision/horizon/balance.
If needed, propose horizon update (use agent_spawn for sub-agents e.g. vision-align, category-balance, lookahead-decompose when complex):
- Map tasks to vision goals.
- Score proposed next 3-5 for category distribution (weights + no excessive repeats across slice/recent).
- Respect depends_on and unblocked.
Persist horizon slice + mix summary to Ruflo memory (and optionally file).
Return the immediate next item + rationale (vision link, category contribution).
Record any planning notes to PROGRESS (or let main flow do it).

The main orchestrator prompt sequences this before execution. Sub-agents (via Ruflo spawn) can be used for individual steps above when the lookahead is complex.

This skill + vision/categories/horizon make the planner extensible, scalable (sub-agents + memory), and decoupled from repo business logic. Harness core never embeds domain prefs.