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.
git clone --depth 1 https://github.com/claude-market/marketplaceWrote 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.
[](https://agentmods.dev/commands/claude-market/marketplace/plan)<a href="https://agentmods.dev/commands/claude-market/marketplace/plan"><img src="https://agentmods.dev/badge/commands/claude-market/marketplace/plan/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.
<a href="https://agentmods.dev/commands/claude-market/marketplace/plan"><img src="https://agentmods.dev/badge/commands/claude-market/marketplace/plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00016 | $0.03517 |
| Opus 5 | $0.00008 | $0.01758 |
| Sonnet 5 | $0.00003 | $0.00703 |
| Haiku 4.5 | $0.00002 | $0.00352 |
Grade A, and why
plan 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 579 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SpecForge Planning Agent
Analyze feature requirements and propose coordinated changes to both OpenAPI spec and database schema.
Overview
SpecForge's core innovation is the dual-spec approach: both OpenAPI and database schemas drive development. This planning command helps you:
- Analyze feature requirements
- Propose OpenAPI spec changes
- Propose database schema changes
- Generate implementation plan
- Estimate complexity and agent requirements
Planning Process
Step 1: Gather Feature Requirements
Ask the user what feature they want to implement. Use AskUserQuestion to collect:
- Feature description: What functionality should this add?
- User-facing behavior: What does the user see/experience?
- Data requirements: What data needs to be stored/retrieved?
- Integration points: Does this interact with existing features?
Step 2: Analyze Current State
Read and analyze existing specifications:
# Read current OpenAPI spec
cat spec/openapi.yaml
# Read existing database migrations
ls -la migrations/
cat migrations/*.sql
# Check existing backend code structure
find backend -type f -name "*.rs" -o -name "*.ts" -o -name "*.py" -o -name "*.go" | head -20
Understand:
- Current API endpoints
- Existing database schema
- Current data models
- Existing patterns and conventions
Step 3: Propose OpenAPI Spec Changes
Based on the feature requirements, draft new OpenAPI endpoints with:
Detailed Endpoint Specifications
paths:
/api/users/{id}/orders:
get:
summary: Get user's orders
description: |
Retrieve all orders for a specific user.
Business Logic:
1. Authenticate the requesting user
2. Verify user has permission to view these orders
3. Fetch user from database by ID
4. Query orders with user_id foreign key
5. Include order items with product details via JOIN
6. Calculate order totals (sum of item prices)
7. Sort by created_at DESC (most recent first)
8. Return paginated results
Edge Cases:
- User not found: Return 404
- No orders: Return empty array with 200
- Permission denied: Return 403
- Invalid pagination params: Return 400
Performance Considerations:
- Use database indexes on user_id and created_at
- Limit JOIN depth to avoid N+1 queries
- Default page size: 20, max: 100
- Consider caching for frequently accessed users
parameters:
- name: id
in: path
required: true
schema:
type: integer
format: int64
description: User ID
- name: page
in: query
schema:
type: integer
default: 1
minimum: 1
description: Page number for pagination
- name: limit
in: query
schema:
type: integer
default: 20
minimum: 1
maximum: 100
description: Number of orders per page
responses:
"200":
description: User's orders retrieved successfully
content:
application/json:
schema:
type: object
properties:
data:
type: array
items:
$ref: "#/components/schemas/Order"
pagination:
type: object
properties:
page:
type: integer
limit:
type: integer
total:
type: integer
totalPages:
type: integer
examples:
success:
value:
data:
- id: 1
userId: 123
total: 4999
status: completed
createdAt: "2025-01-15T10:30:00Z"
items:
- productId: 456
quantity: 2
price: 2499
pagination:
page: 1
limit: 20
total: 45
totalPages: 3
"404":
description: User not found
content:
application/json:
schema:
$ref: "#/components/schemas/Error"
"403":
description: Permission denied
content:
application/json:
schema:
$ref: "#/components/schemas/Error"
components:
schemas:
Order:
type: object
required:
- id
- userId
- total
- status
- createdAt
properties:
id:
type: integer
format: int64
description: Unique order identifier
userId:
type: integer
format: int64
description: ID of user who placed the order
total:
type: integer
description: Total price in cents
example: 4999
status:
type: string
enum: [pending, completed, cancelled]
description: Current order status
createdAt:
type: string
format: date-time
description: When order was created
items:
type: array
items:
$ref: "#/components/schemas/OrderItem"
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.
- 10d ago First seen · 579 lines · 16 tokens per session scan A fbc9bf716c3d
plan is a command published in the GitHub repository claude-market/marketplace (22 stars, last pushed 10mo ago), licensed MIT. It adds 16 tokens to every session and 3,517 once invoked, about $0.0001 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.
Other commands, from other repositories
init
Initialize configurations for Supabase local development.
http-service
Build, review or debug a Bun HTTP service. Loads the http-service skill, then works the task through its workflow.
start-10-1
A guided lesson on setting up clasp, a command-line tool for managing Google Apps Script projects, and connecting it to Google’s Apps Script API.
api-contract-review
Review an API contract (endpoints, request/response shapes, error codes, auth model) BEFORE implementation for naming consistency, versioning, pagination, idempotency, and alignment with existing endpoints. Distinct from review-hard (post-implementation risk) and repo-consistency-sweep (pattern matching on written…
build
Discover an AI Gateway's models and MCP tools, retrieve a credential, and integrate them into your app — call a model, connect MCP tools, or scaffold a runnable agent.
fastapi
FastAPI application design and implementation conventions. Use this skill when building, updating, or reviewing FastAPI services, routers, dependencies, request/response schemas, streaming endpoints, or API tests. Trigger on FastAPI-specific work such as path operation design, dependency injection, response models…