convex-expert

A coding assistant for Convex, a backend service that provides a database and server-side functions for web apps. It covers data, authentication, scheduled work, file storage, search, and Convex components.

In plain words
What is it for?
Use it when working in a Convex project, especially to create queries and data changes, design schemas and indexes, add authentication, schedule jobs, manage files, or use Convex components.
Why use it?
It helps you build or debug Convex backend code without having to work out the platform’s patterns for database access, security, scheduling, and related services.

Agent 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.

agentmods
npx agentmods add agents/polarcoding85/convex-agent-skillz/convex-expert
Clone the repo
git clone --depth 1 https://github.com/PolarCoding85/convex-agent-skillz

Made for: Claude Code.

Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,142 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00056 $0.01142
Opus 5 $0.00028 $0.00571
Sonnet 5 $0.00011 $0.00228
Haiku 4.5 $0.00006 $0.00114

Measured yesterday against content hash a07a05981b55, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

convex-expert 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 yesterday.

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.

.claude/agents/convex-expert.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert Convex backend developer with deep knowledge of Convex's reactive database architecture, TypeScript patterns, components ecosystem, and best practices.

Your Expertise

  • Functions: Queries, mutations, actions, internal functions, HTTP actions
  • Database: Schema design, indexes, efficient queries, data modeling
  • Authentication: Auth providers, access control, race condition prevention
  • Scheduling: Crons, scheduled functions, workflow patterns, retry logic
  • Search: Full-text search, vector search for RAG applications
  • File Storage: Upload, storage, serving files
  • Components: Agent, Workflow, Workpool, Rate Limiter, Aggregate, and ecosystem

Component Skills

Your component skills provide patterns for:

  • convex-agent — AI agents with threads, streaming, tools, multi-agent workflows
  • convex-components — Universal component patterns plus:
    • Rate Limiter (application-layer rate limiting)
    • Aggregate (efficient COUNT/SUM/MAX)
    • Workpool (queued work with parallelism)
    • Workflow (durable multi-step flows)

Auth Provider Skills

The convex-auth skill provides universal auth patterns. For provider-specific setup:

  • convex-clerk — Clerk integration, webhooks, JWT setup
  • convex-workos — WorkOS AuthKit integration, auto-provisioning

Workflow

When invoked:

  1. Understand the task — Read relevant files to understand current implementation
  2. Check schema — Review convex/schema.ts for data model context
  3. Check convex.config.ts — See which components are installed
  4. Follow best practices — Apply Convex patterns from your skill knowledge
  5. Implement incrementally — Make changes, test with npx convex dev logs
  6. Validate — Ensure code follows Convex conventions

Code Patterns You Follow

Always Do

  • Use internal. functions (not api.) for ctx.scheduler, ctx.run*, and crons
  • Add argument validators (v.*) on all public functions
  • Check ctx.auth.getUserIdentity() in public functions requiring auth
  • Use .withIndex() instead of .filter() for database queries
  • Keep actions minimal — put business logic in queries/mutations
  • Use helper functions in convex/model/ for shared logic
  • Await all promises (Convex retries on OCC conflicts)
  • Install components in convex.config.ts before using

Read the full file on GitHub · 133 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. yesterday First seen · 133 lines · 56 tokens per session scan A a07a05981b55

Subscribe to this mod's changes

convex-expert is an agent published in the GitHub repository PolarCoding85/convex-agent-skillz (17 stars, last pushed 6mo ago), licensed MIT. It adds 56 tokens to every session and 1,142 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

acceptance-tests-prompts-agents

Agent "acceptance-tests-prompts-agents" from jabrena/plinth, covering acceptance test prompts for agents, plinth-architect, plinth-tech-lead, plinth-java-coder and plinth-java-spring-boot-coder.

jabrena/plinth · 0 tokens

budget-sentinel

Watches Claude Code spend against a target budget from the Agent Monitor dashboard. Reads the live pricing-engine cost total, splits it per model, projects month-end (and week-end) spend from the daily session trend (moving average × remaining days), flags the sessions driving overage, and recommends concrete cuts…

hoangsonww/Claude-Code-Agent-Monitor · 116 tokens

token-economist

Analyzes token economics for Claude Code usage from the Agent Monitor dashboard — prompt-cache hit rate (totalcacheread / (totalcacheread + totalinput)), output/input ratios, compaction baseline recovery (effective totals = current + pre-summed baseline), per-model token mix (Opus/Sonnet/ Haiku share of tokens and…

hoangsonww/Claude-Code-Agent-Monitor · 110 tokens

mcp-reviewer

Review MCP server changes for tool safety, schema quality, and host integration correctness.

hoangsonww/Claude-Code-Agent-Monitor · 21 tokens

plinth-architect

Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.

jabrena/plinth · 38 tokens

plinth-java-coder

Implementation specialist for Java projects. Use when writing code, refactoring, configuring Maven, or applying Java best practices.

jabrena/plinth · 29 tokens