planner

A software planning assistant that turns a vague feature request into requirements, an architecture, tasks, dependencies, risks, and an implementation approach.

In plain words
What is it for?
Use it to plan features such as OAuth or real-time notifications, create dependency graphs and phased rollouts, and include testing tasks from the beginning.
Why use it?
It prevents teams from starting to code before they understand the work, its order, and its potential problems.

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/nxtg-ai/forge-plugin/planner
Clone the repo
git clone --depth 1 https://github.com/nxtg-ai/forge-plugin
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 2,051 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 $0.02051
Opus 5 $0.00000 $0.01026
Sonnet 5 $0.00000 $0.00410
Haiku 4.5 $0.00000 $0.00205

Measured 2d ago against content hash a5fbeb6371d5, 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.

docs/agents/planner.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Planner

Transforms vague feature ideas into structured, executable implementation plans with dependency graphs, risk analysis, and phased rollout strategies.

Level L1 Vibe Coder
Category Core Workflow
Model Sonnet

What It Does

The Planner is the strategic architect you wish you had on every project. When you say "I need OAuth" or "we should add real-time notifications," it does not jump to code. Instead, it runs a five-phase planning framework: requirements gathering, architecture design, task breakdown, risk analysis, and implementation strategy. Each phase produces concrete artifacts -- not handwavy recommendations, but actual plan files written to .claude/plans/ with YAML frontmatter, dependency graphs, and time estimates.

What makes the Planner valuable is what it encodes about good software planning. It enforces SOLID principles in every architecture it designs. It recommends clean architecture layers (Interface, Application, Domain, Infrastructure) with dependencies flowing inward. It insists on test strategies alongside implementation plans -- not as an afterthought, but as first-class tasks with coverage targets. It knows that a "simple" feature like user preferences actually involves schema design, migration strategy, API endpoints, validation, and frontend state management.

Without the Planner, you either start coding immediately and discover architectural problems mid-sprint, or you spend an hour sketching in a notebook that nobody references again. The Planner produces living documents that track progress, record decisions, and serve as contracts between you and the agents that execute the work.

When to Use It

  • Starting a new feature from scratch: When you have an idea but no clear path from concept to production, the Planner decomposes it into a plan with task dependencies, time estimates, and risk mitigations.
  • Facing a complex refactoring: When your database layer is tangled or your monolith needs breaking apart, the Planner creates a current-state analysis, target-state design, and a step-by-step transformation path with rollback strategies.
  • Deciding between architectural approaches: When you need to choose between PostgreSQL and MongoDB, REST and GraphQL, or monolith and microservices, the Planner presents explicit trade-offs and recommends based on your project's constraints.
  • Breaking down an epic into sprint-sized tasks: When a feature is too large for a single session, the Planner creates phased milestones with testable outcomes at each checkpoint.

Read the full file on GitHub · 127 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 · 127 lines · 0 tokens per session scan A a5fbeb6371d5

Subscribe to this mod's changes

planner is an agent published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,051 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.