convex-domain-folder

convex-domain-folder is a skill for Claude Code from kellykampen/agent-skills. It costs 226 tokens per session (3,881 once invoked), scanned A, original, MIT.

A folder structure for organizing a Convex backend by business area, such as users, tasks, or companies. Convex is a backend platform with database tables and server functions.

In plain words
What is it for?
It structures schemas, queries, mutations, shared helpers, tests, and HTTP routes inside domain folders while composing them through root files.
Why use it?
Flat backend files become difficult to navigate as an application grows. Grouping each area's tables and functions keeps related code together and controls which functions are public or private.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import type { ConvexEnv } from "../lib/honoHelpers";.

Part of the agent-skills plugin — 25 skills, 7 commands shipped together

Good fit It structures schemas, queries, mutations, shared helpers, tests, and HTTP routes inside domain folders while composing them through root files.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/kellykampen/agent-skills
agentmods
npx agentmods add skills/kellykampen/agent-skills/convex-domain-folder

Made for: Claude Code.

Or install agent-skills, the plugin that ships this one along with the rest of its 25 skills, 7 commands.

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 convex-domain-folder

README.md
[![agentmods](https://agentmods.dev/badge/skills/kellykampen/agent-skills/convex-domain-folder/github.svg)](https://agentmods.dev/skills/kellykampen/agent-skills/convex-domain-folder)
Your own site
<a href="https://agentmods.dev/skills/kellykampen/agent-skills/convex-domain-folder"><img src="https://agentmods.dev/badge/skills/kellykampen/agent-skills/convex-domain-folder/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 convex-domain-folder

Your own site · 80×15
<a href="https://agentmods.dev/skills/kellykampen/agent-skills/convex-domain-folder"><img src="https://agentmods.dev/badge/skills/kellykampen/agent-skills/convex-domain-folder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 226 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,881 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 $0.00226 $0.03881
Opus 5 $0.00113 $0.01940
Sonnet 5 $0.00045 $0.00776
Haiku 4.5 $0.00023 $0.00388

Measured 11d ago against content hash 4213d4748aec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

convex-domain-folder 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.

skills/engineering/convex-domain-folder/SKILL.md · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Convex domain-folder structure

The mental model

A Convex backend tends to start flat: convex/tasks.ts, convex/users.ts, one giant convex/schema.ts. As it grows, the clean end state is one folder per domain, where each domain owns its tables and its functions:

convex/
  schema.ts              # just spreads: ...usersTables, ...tasksTables, ...
  http.ts                # thin composition root: calls each registerXRoutes(app)
  tasks/
    schema.ts            # exports tasksTables (table defs, NOT defineSchema)
    queries.ts           # api.tasks.queries.*  (single-tier domain, no trust split needed)
    mutations.ts         # api.tasks.mutations.*
    model.ts             # shared helpers/validators (no Convex functions)
    tasks.test.ts        # co-located test (needs glob re-rooting, see below)
  companies/
    schema.ts            # data-only domain -> schema.ts is the ONLY file
  users/
    schema.ts            # exports usersTables
    helpers.ts            # shared helpers, used across ALL tiers below (not tiered itself)
    validators.ts          # shared validators, ditto
    triggers.ts            # Convex triggers, ditto
    internal/
      queries.ts          # api path: internal.users.internal.queries.*  (internalQuery)
      mutations.ts        # internalMutation — convex-only, never client-callable
    private/
      queries.ts          # api.users.private.queries.*  (query, requires an authed user)
      mutations.ts        # api.users.private.mutations.*
      actions.ts           # action, also requires an authed user
    public/
      queries.ts           # api.users.public.queries.*  (query, no auth required)

The root schema.ts becomes a thin composition root — a few imports and spreads, zero inline table definitions. Adding a new domain then costs one import + one spread, with no central file to keep editing.

The single most important fact: moving a file into a subfolder changes its Convex function paths, because Convex derives module names from the file path. convex/tasks.tsapi.tasks.*; convex/tasks/queries.tsapi.tasks.queries.*. Every call site must be repointed. This is not a pure rename — plan for the blast radius before you start.

Read the full file on GitHub · 337 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 · 337 lines · 226 tokens per session scan A 4213d4748aec

Subscribe to this mod's changes

convex-domain-folder is a skill published in the GitHub repository kellykampen/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 226 tokens to every session and 3,881 once invoked, about $0.0011 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 2026-08-31.

Related

Other skills, from other repositories

event-store-design

Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.

wshobson/agents · 33 tokens

convex-explain-app

Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.

openclaw/clawhub · 47 tokens

platform-custom-field-generate

Use this skill when users need to create, generate, or validate Salesforce Custom Field metadata. Trigger when users mention custom fields, field types, Roll-up Summary fields, Master-Detail relationships, Lookup relationships, formula fields, picklists, dependent (controlling) picklists, referencing a value set from…

forcedotcom/sf-skills · 194 tokens

durable-objects

Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.

fcakyon/claude-codex-settings · 22 tokens

field-service-sobject-create-configure

Headless 360 REST API deployment step for creating sObject records. Handles describe-based field discovery, required-field derivation, entity-relationship ordering, and composite graph transactions. Use this skill when a designer skill (or a user directly) needs to create sObject records after design confirmation…

forcedotcom/sf-skills · 74 tokens

nornicdb-grpc

Drive NornicDB over gRPC — the Qdrant-compatible surface (Collections, Points, Snapshots) plus the additive NornicSearch service. Use when ingesting via Qdrant SDKs, migrating from Qdrant, or running hybrid text+vector search from a non-Bolt client. Covers connection, RPC catalog, collection→database mapping…

orneryd/NornicDB · 98 tokens