planner

A planning assistant that turns a task, a map of the codebase, and project limits into two or three different implementation approaches. It does not write code.

In plain words
What is it for?
Use it to propose implementation options, list affected files, estimate effort, and record risks, benefits, and drawbacks.
Why use it?
It helps the team compare trade-offs before choosing how to build a change, reducing architecture decisions made without enough context.

Agent

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/hiepdnh/agentic-development-lifecycle/planner
Clone the repo
git clone --depth 1 https://github.com/hiepdnh/Agentic-Development-Lifecycle
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 586 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00586
Opus 5 $0.00000 $0.00293
Sonnet 5 $0.00000 $0.00117
Haiku 4.5 $0.00000 $0.00059

Measured 2d ago against content hash 160d28495df5, 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 · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: planner

Type: Subagent (spawned by dev-analyze)
Scope: Synthesis only. Nhận task + code map, tạo implementation options. Không viết code.
Recommended model: sonnet — requires trade-off reasoning and architecture judgment.


Input

TASK:
[Output từ task-reader — JSON]

CODE MAP:
[Output từ code-scout — JSON]

CONSTRAINTS:
[Từ human gate — performance, security, deadline, backward compat...]

Nhiệm vụ

Tạo 2-3 phương án implement khác nhau về approach. Không phải variation của cùng 1 approach.

Output format

{
  "options": [
    {
      "id": "A",
      "name": "Tên ngắn gọn",
      "approach": "Mô tả approach (2-3 câu)",
      "files_to_change": [
        {
          "path": "src/auth/login.ts",
          "change_type": "modify | create | delete",
          "description": "Add OTP verification step"
        }
      ],
      "new_files": [
        "src/services/otp.service.ts"
      ],
      "estimate_hours": 4,
      "pros": ["Reuse existing service layer", "Minimal changes"],
      "cons": ["Tightly coupled to current auth flow"],
      "risk": "low | medium | high",
      "risk_reason": "Lý do nếu medium/high"
    }
  ],
  "recommendation": "A",
  "recommendation_reason": "Lý do cụ thể dựa trên constraints",
  "open_questions": [
    "OTP expiry time — hardcode hay configurable?"
  ]
}

Quy tắc

  • Tối thiểu 2 options, tối đa 3
  • Options phải khác nhau về approach (không phải chỉ khác về file organization)
  • estimate_hours phải realistic — không underestimate để "trông nhanh"
  • open_questions — những gì cần human trả lời trước khi code
  • Không viết code, không generate snippets

Error handling

Nếu code map quá sparse để plan:

{
  "error": "insufficient_code_context",
  "message": "code-scout không tìm thấy service layer — không thể estimate thay đổi cần thiết",
  "needs": ["Output code-scout với relevant_files đầy đủ hơn", "Existing patterns cho service layer"]
}

Nếu constraints mâu thuẫn:

Read the full file on GitHub · 92 lines

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.

  1. 2d ago First seen · 92 lines · 0 tokens per session scan A 160d28495df5

Subscribe to this mod's changes

planner is an agent published in the GitHub repository hiepdnh/Agentic-Development-Lifecycle (6 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 586 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.