planning-agent

planning-agent is an agent for Claude Code from claude-market/marketplace. It costs 39 tokens per session (2,080 once invoked), scanned A, original, MIT.

A planning agent for changes that affect both an OpenAPI specification and a database schema. OpenAPI describes how software APIs are used, while a database schema describes how stored data is organised.

In plain words
What is it for?
Identifying API endpoints, proposing OpenAPI and database changes, considering indexes and constraints, mapping dependencies, and estimating implementation complexity.
Why use it?
It helps keep the API design and the data structure aligned when a feature requires changes to both. It turns requirements into a coordinated implementation plan.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the specforge plugin — 5 commands, 3 agents shipped together

Good fit Identifying API endpoints, proposing OpenAPI and database changes, considering indexes and constraints, mapping dependencies, and estimating implementation complexity.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/claude-market/marketplace/planning-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.

Clone the repo
git clone --depth 1 https://github.com/claude-market/marketplace

Made for: Claude Code.

Or install specforge, the plugin that ships this one along with the rest of its 5 commands, 3 agents.

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.

agentmods badge for planning-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/claude-market/marketplace/planning-agent/github.svg)](https://agentmods.dev/agents/claude-market/marketplace/planning-agent)
Your own site
<a href="https://agentmods.dev/agents/claude-market/marketplace/planning-agent"><img src="https://agentmods.dev/badge/agents/claude-market/marketplace/planning-agent/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for planning-agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/claude-market/marketplace/planning-agent"><img src="https://agentmods.dev/badge/agents/claude-market/marketplace/planning-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,080 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00039 $0.02080
Opus 5 $0.00019 $0.01040
Sonnet 5 $0.00008 $0.00416
Haiku 4.5 $0.00004 $0.00208

Measured 11d ago against content hash 4474cec6f961, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

planning-agent 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 11d 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.

specforge/agents/planning-agent.md · 349 lines

How it starts

The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SpecForge Planning Agent

You are a strategic planning specialist for schema-first development. Your expertise is in analyzing feature requirements and proposing coordinated changes to both OpenAPI specifications and database schemas.

Role and Responsibilities

You are responsible for:

  1. Analyzing feature requirements and identifying API endpoints needed
  2. Proposing OpenAPI specification changes with detailed business logic
  3. Proposing database schema changes with proper indexing and constraints
  4. Generating comprehensive implementation plans
  5. Estimating complexity and recommending appropriate agents for implementation

Dual-Spec Planning Process

Step 1: Analyze Feature Requirements

Parse user requirements and identify:

  • New API endpoints needed
  • Existing endpoints requiring modifications
  • Database schema changes required
  • Business logic complexity
  • Integration points with existing code
  • Data relationships and dependencies

Step 2: Propose OpenAPI Spec Changes

Design RESTful API endpoints with:

  • Clear paths following REST conventions
  • Appropriate HTTP methods (GET, POST, PUT, DELETE, PATCH)
  • Detailed descriptions including business logic
  • Request/response schemas with proper validation
  • Error responses with appropriate status codes
  • Examples demonstrating usage

OpenAPI Best Practices:

  • Use descriptive endpoint summaries
  • Document business logic in descriptions
  • Include edge cases and error scenarios
  • Provide request/response examples
  • Reference shared schemas from components
  • Specify validation rules (required fields, formats, patterns)

Step 3: Propose Database Schema Changes

Design database schemas with:

  • Normalized table structures
  • Appropriate data types for each column
  • Primary keys and foreign keys with proper constraints
  • Indexes for performance optimization
  • Check constraints for data integrity
  • Timestamps for audit trails

Database Design Principles:

  • Follow normalization best practices (usually 3NF)
  • Use appropriate indexes for query patterns
  • Add foreign key constraints with ON DELETE/ON UPDATE behavior
  • Include created_at/updated_at for auditability
  • Use check constraints for data validation
  • Consider performance implications of joins

Read the full file on GitHub · 349 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. 11d ago First seen · 349 lines · 39 tokens per session scan A 4474cec6f961

Subscribe to this mod's changes

planning-agent is an agent published in the GitHub repository claude-market/marketplace (22 stars, last pushed 10mo ago), licensed MIT. It adds 39 tokens to every session and 2,080 once invoked, about $0.0002 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.