feathers-expert

feathers-expert is an agent for Claude Code from hassan4702/feathers-plugin. It costs 81 tokens per session (574 once invoked), scanned A, original, MIT.

An expert coding agent for FeathersJS version 5, a JavaScript framework for building APIs and real-time applications. It handles questions involving services, hooks, schemas, authentication, events, and database adapters.

In plain words
What is it for?
Use it for architecture choices, missing endpoints, access-control flows, real-time events, query syntax, schemas, hooks, and database connections.
Why use it?
It helps diagnose Feathers problems that cross several files or involve how the framework's parts work together.

Agent for Claude Code

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

Part of the feathersjs plugin — 4 skills, 1 agent shipped together

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/hassan4702/feathers-plugin/feathers-expert
Clone the repo
git clone --depth 1 https://github.com/hassan4702/feathers-plugin

Made for: Claude Code.

Or install feathersjs, the plugin that ships this one along with the rest of its 4 skills, 1 agent.

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 feathers-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/hassan4702/feathers-plugin/feathers-expert.svg)](https://agentmods.dev/agents/hassan4702/feathers-plugin/feathers-expert)
Your own site
<a href="https://agentmods.dev/agents/hassan4702/feathers-plugin/feathers-expert"><img src="https://agentmods.dev/badge/agents/hassan4702/feathers-plugin/feathers-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 574 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 5.1 $0.00081 $0.00574
Opus 5 $0.00041 $0.00287
Sonnet 5 $0.00016 $0.00115
Haiku 4.5 $0.00008 $0.00057

Measured 6d ago against content hash 8601e6781e9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

feathers-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 6d 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.

agents/feathers-expert.md · 21 lines

What it actually says

You are a FeathersJS v5 (Dove) expert. You know the framework deeply:

  • Services are transport-independent CRUD objects (find/get/create/update/patch/remove + setup/teardown). The same method serves REST, websockets, and internal calls. Mutating methods emit created/updated/patched/removed events — this is how real-time works.
  • Hooks are around/before/after/error middleware registered per method via app.service(path).hooks({...}), with all running first. Around hooks take (context, next) and must await next(); before/after/error take (context).
  • Schemas & resolvers use TypeBox. Four resolver kinds: result (populate associations), data (defaults/computed/hashing), query (row-level security), external (hide secrets). Types are derived with Static<typeof schema>.
  • The four-file service layout: <name>.ts (register + wire hooks), <name>.class.ts (adapter service), <name>.schema.ts (TypeBox + resolvers), <name>.shared.ts (path/methods/client). Services are activated by app.configure(...) in src/services/index.ts.
  • Adapters: @feathersjs/knex (SQL — needs migrations), @feathersjs/mongodb (ObjectId ids, no migrations), @feathersjs/memory.

Approach:

  1. Read the relevant files before answering — an existing sibling service reveals the project's conventions (id type, adapter, ESM/CJS).
  2. Diagnose root cause, not symptoms. A 404 usually means the service was never configured; a leaked field means a missing external resolver; an auth bypass usually means authorization lives in the data resolver instead of the query resolver.
  3. Give concrete, idiomatic fixes that match the project's existing patterns. Cite the specific file and line.
  4. Prefer the four-file structure and the resolver-based security model over ad-hoc hooks when both work.

When the task is single-file generation or a focused edit, the plugin's feathers-service, feathers-hooks, and feathers-schema skills are usually a better fit than this agent.

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. 6d ago First seen · 21 lines · 81 tokens per session scan A 8601e6781e9c

Subscribe to this mod's changes

feathers-expert is an agent published in the GitHub repository hassan4702/feathers-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 81 tokens to every session and 574 once invoked, about $0.0004 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 agents, from other repositories

call-tracer

Orchestrates parallel call tree tracing using subagents for each entry point category (Controllers, LiveViews, Workers, GenServers). Use proactively when debugging unexpected values, tracing request flow, or planning signature changes.

oliver-kriska/claude-elixir-phoenix · 46 tokens

do-debugger

Autonomous Durable Objects debugger. Automatically detects and fixes DO configuration errors, runtime issues, and common mistakes without user intervention.

secondsky/claude-skills · 28 tokens

better-auth-debugger

Autonomous agent for diagnosing better-auth authentication issues. Analyzes configuration, validates OAuth callbacks, tests endpoints, and provides specific fixes.

secondsky/claude-skills · 32 tokens

fec-performance-optimizer

Front-end performance analysis and optimization specialization: Core Web Vitals, packaging volume, runtime and rendering, network and cache, memory leak troubleshooting; can cooperate with Lighthouse, Bundle analysis and Profiler. Use it when users mention page slowness, lag, first screen, package size, poor…

bovinphang/frontend-craft · 0 tokens

fec-ui-checker

Use this subagent to troubleshoot visual defects, layout confusion, CSS issues, responsive exceptions, and inconsistencies between interaction and design in the front-end UI, and save the report as a Markdown file. Supports obtaining design data from Figma, Sketch, MasterGo, Pixso, Moko, and Mock, compares the design…

bovinphang/frontend-craft · 0 tokens

bug-detector

Detects correctness bugs, logic errors, edge cases, API misuse, and error handling issues in code changes.

liatrio-labs/claude-code-gauntlet · 25 tokens