product-direction

product-direction is a skill for Claude Code, Codex from prisma/orm. It costs 145 tokens per session (2,097 once invoked), scanned C, original, Apache-2.0.

A repository decision skill that compares feature requests, pull requests, and proposed changes with the project's written product direction. It gives a cited verdict while leaving the final decision to a maintainer.

In plain words
What is it for?
It helps review, label, and reply to feature requests or pull requests, recording new decisions and explaining which project document supports each verdict.
Why use it?
It reduces inconsistent triage by checking requests against the project's goals, values, previous decisions, and accepted exclusions.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Good fit It helps review, label, and reply to feature requests or pull requests, recording new decisions and explaining which project document supports each verdict.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/prisma/orm/product-direction
About the project

Prisma ORM is a Node.js and TypeScript database toolkit that lets applications work with databases through a programming interface instead of writing every query directly in SQL. Developers use it with databases including PostgreSQL, MySQL, MariaDB, SQL Server, SQLite, MongoDB, and CockroachDB. The catalogue add-ons provide agent rules, skills, hooks, agents, and other workflows for using Prisma.

prisma/orm · 47,671 stars · on GitHub · prisma.io

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.

Any agent
npx skills add prisma/orm --skill product-direction
Clone the repo
git clone --depth 1 https://github.com/prisma/orm

Made for: Claude Code, Codex.

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 product-direction

README.md
[![agentmods](https://agentmods.dev/badge/skills/prisma/orm/product-direction/github.svg)](https://agentmods.dev/skills/prisma/orm/product-direction)
Your own site
<a href="https://agentmods.dev/skills/prisma/orm/product-direction"><img src="https://agentmods.dev/badge/skills/prisma/orm/product-direction/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 product-direction

Your own site · 80×15
<a href="https://agentmods.dev/skills/prisma/orm/product-direction"><img src="https://agentmods.dev/badge/skills/prisma/orm/product-direction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,097 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00145 $0.02097
Opus 5.5 $0.00058 $0.00839
Sonnet 5.5 $0.00029 $0.00419
Haiku 4.5 $0.00015 $0.00210

Measured today against content hash b44534d177e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

product-direction scanned grade C with 1 finding 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 today.

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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

8. **Never decline a change that a maintainer in the thread proposed or accepted,** unless a later maintainer comment in the thread declines it. Name the maintainer's direction in `bestSolution`. The verdict is never `re
skills-contrib/product-direction/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product direction

Judge a request, and your own proposals, against what the maintainers wrote down. Give a verdict with the line it rests on. Leave the decision to a maintainer. A wrong no drives away the person who asked. A wrong yes commits the maintainers to work they never chose.

Every rule and heading here names its source in references/sources.md.

The record

The record has five parts. Four are pages in the repository. The fifth is the reading rules in this file.

Part What it holds Default path Template
Project intent What the project is, who it is for, what it optimises for and does not need to, what not to assume, agent guidance. docs/direction/project-intent.md project-intent.md
Vision Values and durable themes. Nothing about current work. docs/direction/vision.md vision.md
Decision records One record per no: what to use instead, and what would reopen it. docs/direction/decisions/ decision-record.md
Steering list The accepted nos, one line each, with what to use instead. Read before proposing anything. docs/direction/decisions/index.md steering-list.md
Reading rules How to turn the record into a verdict. This file

Read the full file on GitHub · 95 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. today First seen · 95 lines · 145 tokens per session scan C b44534d177e7

Subscribe to this mod's changes

product-direction is a skill published in the GitHub repository prisma/orm (47,671 stars, last pushed today), licensed Apache-2.0. It adds 145 tokens to every session and 2,097 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-23.