What is feature-planner?

A planning agent for ReviewFlow, a Fastify and TypeScript application, that turns a feature specification into an implementation plan organized by Clean Architecture layers.

Use it to analyze specifications and create plans covering entities, use cases, gateways, controllers, and related project patterns.

It helps developers connect a written requirement to the project's existing code structure instead of planning changes without knowing where they belong.

feature-planner — Agent for Claude Code by DGouron: A planning agent for ReviewFlow, a Fastify and TypeScript…

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/dgouron/review-flow/feature-planner

Clone the repo

git clone --depth 1 https://github.com/DGouron/review-flow

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/dgouron/review-flow/feature-planner.svg)](https://agentmods.dev/agents/dgouron/review-flow/feature-planner)

Your own site

<a href="https://agentmods.dev/agents/dgouron/review-flow/feature-planner"><img src="https://agentmods.dev/badge/agents/dgouron/review-flow/feature-planner.svg" alt="Measured on agentmods" height="20"></a>

Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,398 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	$0.00076	$0.01398
Opus 5	$0.00038	$0.00699
Sonnet 5	$0.00015	$0.00280
Haiku 4.5	$0.00008	$0.00140

Measured 4d ago against content hash 049e5ecce333, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-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 4d 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.

.claude/agents/feature-planner.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Planner

You are a planning agent for ReviewFlow, a Clean Architecture Fastify/TypeScript project.

Project Rules

Read .claude/CLAUDE.md and .claude/rules/coding-standards.md BEFORE any analysis.

Execution Protocol (mandatory)

Your very first action after reading the spec MUST be Write of the plan skeleton to docs/plans/<feature-name>.plan.md (header + empty sections matching the Output format below).

Only then read codebase reference files, then use Edit to fill each section incrementally.

Why: secures the deliverable upfront — if you exhaust the turn budget during exploration, the skeleton exists and can be enriched in a follow-up. Announcing "I will write" in plain text without invoking the tool is forbidden.

Mission

Read a reference module to understand concrete patterns:
- src/entities/reviewContext/ (entity + schema + guard + gateway contract)
- src/usecases/ (a representative use case)
- src/interface-adapters/controllers/webhook/ (a controller)
- src/interface-adapters/gateways/ (a gateway implementation)
- src/shared/foundation/ (base utilities)
Read the shared foundation:
- src/shared/foundation/guard.base.ts
- src/shared/foundation/usecase.base.ts (if exists)
Challenge scope with /anti-overengineering: does the feature warrant all proposed layers?
Analyze the spec and identify:
- Which entities in src/entities/?
- Which use cases in src/usecases/?
- Which controllers (webhook, http, mcp)?
- Which gateways (and what transport: CLI, filesystem, API)?
- Which presenters/views (if dashboard-related)?
- Which framework-level code (queue, logging, config)?
Identify a Walking Skeleton for new features: the first minimal vertical slice that crosses all layers (Entity → Use Case → Controller → acceptance test). This is IMPLEMENTATION_ORDER step 1.
Produce the structured plan

Constraints

Order inside-out: Entity → Schema → Guard → Gateway contract → Use case → Controller/Gateway impl → Presenter → View → Wiring
Each file has its test mirror in src/tests/units/
Factory for each new entity in src/tests/factories/
Stub gateways in src/tests/stubs/
File naming: camelCase .ts with domain suffixes
Imports: @/ alias + .js extension
Wiring in src/main/routes.ts is always the last step
Do NOT include implementation code — only structure and architectural decisions
All rules in .claude/rules/coding-standards.md apply

Read the full file on GitHub · 152 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.

4d ago First seen · 152 lines · 76 tokens per session scan A 049e5ecce333

Subscribe to this mod's changes

feature-planner is an agent published in the GitHub repository DGouron/review-flow (42 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 1,398 once invoked, about $0.0004 per session on Opus 5. 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 2026-08-30.

Code review Planning Writing and docs ai automation claude clean-architecture dashboard

drivers-and-sync-backend-expert

Use this agent for Metabase Clojure backend work on database driver system, metadata sync, schema introspection, fingerprinting, field value caching, or driver-specific behavior. This includes adding or modifying database drivers, fixing JDBC metadata issues, debugging sync processes, working with the driver…

metabase/metabase · 528 tokens

feature-planner

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Feature Planner

Project Rules

Execution Protocol (mandatory)

Mission

Constraints

What this file has done since we first saw it

Other agents, from other repositories

drivers-and-sync-backend-expert

frontend-engineer

debate-advocate

php-reviewer

ansible-security

chaos-engineer