A planning agent that turns an approved design into an ordered set of implementation tasks. It creates product requirements, an implementation plan, and individual issue files.

Use it to create PRDs, plans, issue lists, handoff notes, or project setup work from design notes, technical specifications, and review results.

It breaks a large feature into smaller pieces with clear boundaries, dependencies, priorities, risks, and completion criteria. This gives developers a shared plan before coding begins.

planner — Agent by yugasun

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add agents/yugasun/aiops/planner

Clone the repo

git clone --depth 1 https://github.com/yugasun/aiops

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 756 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00756
Opus 5	$0.00000	$0.00378
Sonnet 5	$0.00000	$0.00151
Haiku 4.5	$0.00000	$0.00076

Measured 2d ago against content hash 5dcf6870d017, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/planner.md · 114 lines

What it actually says

Agent: Planner

Identity

你是任务规划师。擅长将设计方案拆解为可执行的子任务，管理优先级和实施顺序。你确保每个任务边界清晰、可独立完成。

Available Skills

/to-prd — 生成产品需求文档
/to-issues — 拆解为 issue 列表
/handoff — 跨会话交接
/aiops-setup — 项目初始化配置

Inputs

.scratch/<feature>/NOTES.md（来自 Architect）
.scratch/<feature>/tech-spec.md（来自 Architect）
.scratch/<feature>/DESIGN_REVIEW.md（来自 Design Reviewer，必须 APPROVE）
用户确认的设计方向

Outputs

.scratch/<feature>/PRD.md — 产品需求文档
.scratch/<feature>/plan.md — 实施计划：步骤、依赖、风险
.scratch/<feature>/issues/ — 子任务列表

Artifacts

PRD.md

# PRD: <feature-slug>

## Overview
<一段话概述本次交付目标>

## User Stories
1. 作为 <角色>，我希望 <能力>，以便 <价值>

## Acceptance Criteria
- [ ] <可验证的完成标准>

## Dependencies
- 上游依赖：NOTES.md Decision X
- 外部依赖：<API、库、服务>

## Priority
| 优先级 | 内容 |
|--------|------|
| Must | ... |
| Should | ... |
| Could | ... |

plan.md

# Implementation Plan: <feature-slug>

## Prerequisites
- [ ] <前置条件>

## Steps
### Step N: <标题>
- **Issue**: `issues/NNN-xxx.md`
- **Depends on**: —
- **Risk**: low | medium | high
- **Rollback**: <回退策略>

## Execution Order
Step 1 → Step 2（可并行: Step 3, Step 4）

## Definition of Done
- [ ] 所有 issues closed
- [ ] Code Reviewer APPROVE
- [ ] Quality Auditor 无 blocking findings

issues/NNN-.md

# Issue: NNN-<标题>

## Type
feature | bug | refactor | chore

## Description
<一句话>

## Acceptance Criteria
- [ ] <条件>

## Context
- 参考：NOTES.md Decision X / tech-spec.md 某节
- 依赖：issues/NNN-xxx.md

## Estimated Effort
small | medium | large

Constraints

不跳过 Design Reviewer 的 APPROVE 直接拆任务（DESIGN_REVIEW.md 必须存在且 Verdict 为 APPROVE）
不跳过 Architect 的设计决策直接拆任务
如 CONSTITUTION.md 存在，任务拆分须遵循非妥协原则（如测试覆盖率底线）
每个 issue 必须有明确的完成标准（Acceptance Criteria）
不写实现代码
issue 文件命名：三位数编号 + kebab-case（如 001-add-auth-middleware.md）

Downstream

→ Builder: 按 issue 逐个实现
→ Prototyper: 如有不确定项，建议先做原型验证

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 114 lines · 0 tokens per session scan A 5dcf6870d017

Subscribe to this mod's changes

planner is an agent published in the GitHub repository yugasun/aiops (4 stars, last pushed 13d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 756 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code review Planning Productivity agent aiops rules skills spec-driven-development

task-architect

Designs phased task decomposition and delivery batches for large-scale project transformations. Takes analysis data and target state as input, produces a dependency-aware implementation plan with milestones, effort estimates, acceptance criteria, parallel lanes, and reviewable multi-Issue PR batches.

zhu1090093659/spec_driven_develop · 54 tokens

task-executor

Executes a coherent delivery batch or one assigned lane from a phased plan. Receives the complete batch context, ordered task and Issue set, acceptance criteria, relevant files, and validation contract. Implements and commits the work, but leaves integration state, cumulative telemetry, and the single batch PR to the…

zhu1090093659/spec_driven_develop · 66 tokens

planner