specforge

specforge is a plugin for Claude Code from claude-market/marketplace. Its manifest loads nothing; the 5 commands, 3 agents it bundles cost 176 tokens per session together, scanned A, original, MIT.

A plugin for building applications from two linked definitions: an OpenAPI document, which describes HTTP APIs, and a database schema, which describes stored data. It includes commands and agents for planning, building, validating, testing, syncing, and shipping.

In plain words
What is it for?
Use it to start a schema-first project, plan features, generate or build backend code, validate the definitions, run tests, synchronize changes, and prepare a release.
Why use it?
It keeps API behavior, database structure, generated code, and implementation work based on shared definitions. This reduces manual coordination between those parts of an application.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add claude-market/marketplace
agentmods
npx agentmods add plugins/claude-market/marketplace/specforge
Clone the repo
git clone --depth 1 https://github.com/claude-market/marketplace

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.

agentmods badge for specforge

README.md
[![agentmods](https://agentmods.dev/badge/plugins/claude-market/marketplace/specforge.svg)](https://agentmods.dev/plugins/claude-market/marketplace/specforge)
Your own site
<a href="https://agentmods.dev/plugins/claude-market/marketplace/specforge"><img src="https://agentmods.dev/badge/plugins/claude-market/marketplace/specforge.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 5 commands, 3 agents cost 176 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

specforge 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 3d 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/.claude-plugin/plugin.json · 41 lines

What it actually says

{
  "name": "specforge",
  "version": "0.1.2",
  "description": "Schema-first development ecosystem with dual-spec workflows (OpenAPI + DB schema) for building production-ready applications through deterministic code generation and intelligent orchestration",
  "author": {
    "name": "Daniel Emod Kovacs",
    "url": "https://github.com/danielkov"
  },
  "repository": "https://github.com/claude-market/marketplace/tree/main/specforge",
  "license": "MIT",
  "keywords": [
    "specforge",
    "openapi",
    "schema-first",
    "code-generation",
    "orchestration",
    "api-development",
    "database-schema",
    "type-safety"
  ],
  "commands": [
    "./commands/init.md",
    "./commands/plan.md",
    "./commands/build.md",
    "./commands/validate.md",
    "./commands/test.md",
    "./commands/ship.md",
    "./commands/sync.md"
  ],
  "agents": [
    "./agents/captain-orchestrator.md",
    "./agents/planning-agent.md",
    "./agents/validation-agent.md"
  ],
  "skills": [
    "./skills/openapi-expert.md",
    "./skills/stack-advisor.md",
    "./skills/integration-expert.md"
  ]
}
Contents

What it installs

The manifest is a name and a version. 5 commands, 3 agents travel with it, and installing the plugin installs all of them — 176 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 3d ago First seen · 41 lines scan A c19e06105533

Subscribe to this mod's changes

specforge is a plugin published in the GitHub repository claude-market/marketplace (22 stars, last pushed 10mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Related

Other plugins, from other repositories

google-plugins marketplace

Plugin marketplace listing 17 plugins: alloydb, alloydb-omni, bigtable, cloud-sql-mysql, cloud-sql-postgresql.

google/skills · not measured

butterbase-skills

Build full-stack apps with Butterbase — AI-Native Backend-as-a-Service. Skills for app creation, schema design, frontend deployment, RLS debugging, serverless functions, and contributing.

butterbase-ai/butterbase-skills · not measured

sql-database-pipeline

Build SQL database pipelines with dlt: connect to any SQL source, load tables to a destination, tune performance with backends.

dlt-hub/dlthub-ai-harness · not measured

sap-abap

Comprehensive ABAP development skill for SAP systems. Use when writing ABAP code, working with internal tables, structures, ABAP SQL, object-oriented programming, RAP (RESTful Application Programming Model), CDS views, EML statements, ABAP Cloud development, string processing, dynamic programming, RTTI/RTTC, field…

DayronDLR/sap-enterprise-stack-plugin · not measured

reporting-and-database-access

MATLAB, Database Toolbox, MATLAB Report Generator, Parallel Computing Toolbox, and Simulink Report Generator.

matlab/matlab-agentic-toolkit · not measured

postgres-sql

The PostgreSQL SQL dialect & data types that set Postgres apart from generic SQL. Use when writing or debugging Postgres-specific SQL — upsert (ON CONFLICT), RETURNING, MERGE, CTEs, window frames, GROUPING SETS, LATERAL, generated/identity columns, partitioning, jsonb/jsonpath/SQL-JSON (JSONTABLE), array.

dashed/claude-marketplace · not measured