feathers-review

feathers-review is a skill for Claude Code from hassan4702/feathers-plugin. It costs 127 tokens per session (979 once invoked), scanned A, original, MIT.

A review guide for FeathersJS version 5 code, including services, hooks, schemas, and pull requests.

In plain words
What is it for?
Use it to audit or review FeathersJS code before release or after generating or editing it.
Why use it?
It checks for common security and correctness problems such as missing login checks, weak ownership controls, and exposed secrets.

Skill for Claude Code

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

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

Good fit Use it to audit or review FeathersJS code before release or after generating or editing it.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hassan4702/feathers-plugin/feathers-review
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 hassan4702/feathers-plugin --skill feathers-review
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-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/hassan4702/feathers-plugin/feathers-review/github.svg)](https://agentmods.dev/skills/hassan4702/feathers-plugin/feathers-review)
Your own site
<a href="https://agentmods.dev/skills/hassan4702/feathers-plugin/feathers-review"><img src="https://agentmods.dev/badge/skills/hassan4702/feathers-plugin/feathers-review/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 feathers-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/hassan4702/feathers-plugin/feathers-review"><img src="https://agentmods.dev/badge/skills/hassan4702/feathers-plugin/feathers-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 979 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 $0.00127 $0.00979
Opus 5 $0.00063 $0.00490
Sonnet 5 $0.00025 $0.00196
Haiku 4.5 $0.00013 $0.00098

Measured 10d ago against content hash 070837fe6e69, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

feathers-review 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.

skills/feathers-review/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FeathersJS Code Review

Walk the changed/affected files and check the items below. Report findings grouped by severity (Critical → Warning → Style), each with the file, the problem, and a concrete fix. Don't just restate the code — say what's wrong and what to change.

Critical (security / correctness)

  1. Authentication present. Each non-public service should have authenticate('jwt') in around.all. Flag any service exposed externally (methods includes mutating verbs) without it. Confirm "public" services are public on purpose.
  2. Authorization actually enforced. Ownership/tenancy checks belong in the query resolver (<name>QueryResolver) so they cover find/get/patch/remove, not only in a data resolver (which misses reads/removes). Verify writes are pinned to context.params.user, not to a client-supplied id.
  3. Sensitive fields hidden. Every schema with secrets (password, tokens, internal ids) needs an external resolver setting them to undefined. A missing external resolver leaks them in API responses.
  4. Ownership derived from auth, not body. userId/ownerId should be set in the data resolver from context.params.user, never trusted from context.data.
  5. Service is registered. The configure function must be app.configure(...)-ed in src/services/index.ts. An unregistered service silently 404s.
  6. Hooks are wired. A hook/resolver that's defined but not added to the .hooks({...}) object never runs — check each validator/resolver is referenced.
  7. additionalProperties: false on data schemas, so unexpected fields are rejected rather than written.
  8. Query surface is minimal. querySyntax(...) should list only properties safe to filter/sort on; sensitive or expensive columns shouldn't be queryable.

Warning (robustness)

  • await next() in around hooks — missing it skips the service call and all downstream hooks.
  • Internal vs external calls — guards that read context.params.user should also consider context.params.provider (undefined = internal) so server-side calls aren't wrongly blocked or wrongly trusted.
  • Typed errors — throw @feathersjs/errors (BadRequest, NotAuthenticated, Forbidden, NotFound) rather than generic Error, so HTTP status codes are correct.
  • Schema ↔ migration drift (SQL) — every new/changed/removed field needs a matching Knex migration with a working down. Flag schema edits with no migration.
  • Unique $id — duplicated schema $id values collide in the validator registry.
  • Pagination — large collections should set/respect paginate; unbounded find is a DoS/perf risk.
  • By-reference mutation of context.data / context.params.query — spread into new objects.

Read the full file on GitHub · 59 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. 10d ago First seen · 59 lines · 127 tokens per session scan A 070837fe6e69

Subscribe to this mod's changes

feathers-review is a skill published in the GitHub repository hassan4702/feathers-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 127 tokens to every session and 979 once invoked, about $0.0006 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

review

Review branch changes against Archcore docs, or report project health. Use for 'review my branch', 'review the changes before merge', 'show status', 'documentation gaps', 'check if docs match code', 'close out the feature', 'ship the feature and close it out', or after a staleness warning. --drift for staleness…

archcore-ai/plugin · 107 tokens

explain

Guided code tour of a file or subsystem this session touched — entry point, the load-bearing pieces, the edges, and what connects to it.

gkaria/vibe-learn · 33 tokens

fec-drawio-studio

An editable workflow for making technical diagrams in draw.io (also called diagrams.net), with the original .drawio file saved alongside exported images or documents. It covers architecture, database, UML, sequence, flow, machine-learning, and code-structure diagrams.

bovinphang/frontend-craft · 154 tokens

fec-nextjs-project-standard

A development guide for Next.js 14 and newer projects using App Router, Next.js’s file-based routing system. It covers server-rendered pages, layouts, data loading, middleware, metadata, and server actions.

bovinphang/frontend-craft · 86 tokens

fec-component-testing

A guide for writing and reviewing front-end unit, component, and lightweight integration tests. These tests check small pieces of code and UI behavior without running a full browser journey.

bovinphang/frontend-craft · 123 tokens

fec-monorepo-project-standard

A guide for organising a monorepo, which is one code repository containing several applications and shared packages. It covers workspace dependencies, folder structure, build tasks, testing, caching, and package releases.

bovinphang/frontend-craft · 62 tokens