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.
npx skills add hassan4702/feathers-plugin --skill feathers-reviewgit clone --depth 1 https://github.com/hassan4702/feathers-pluginWrote 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.
[](https://agentmods.dev/skills/hassan4702/feathers-plugin/feathers-review)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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)
- Authentication present. Each non-public service should have
authenticate('jwt')inaround.all. Flag any service exposed externally (methodsincludes mutating verbs) without it. Confirm "public" services are public on purpose. - Authorization actually enforced. Ownership/tenancy checks belong in the query resolver (
<name>QueryResolver) so they coverfind/get/patch/remove, not only in a data resolver (which misses reads/removes). Verify writes are pinned tocontext.params.user, not to a client-supplied id. - Sensitive fields hidden. Every schema with secrets (
password, tokens, internal ids) needs an external resolver setting them toundefined. A missing external resolver leaks them in API responses. - Ownership derived from auth, not body.
userId/ownerIdshould be set in the data resolver fromcontext.params.user, never trusted fromcontext.data. - Service is registered. The configure function must be
app.configure(...)-ed insrc/services/index.ts. An unregistered service silently 404s. - Hooks are wired. A hook/resolver that's defined but not added to the
.hooks({...})object never runs — check each validator/resolver is referenced. additionalProperties: falseon data schemas, so unexpected fields are rejected rather than written.- 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.usershould also considercontext.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 genericError, 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
$id— duplicated schema$idvalues collide in the validator registry. - Pagination — large collections should set/respect
paginate; unboundedfindis a DoS/perf risk. - By-reference mutation of
context.data/context.params.query— spread into new objects.
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.
- 10d ago First seen · 59 lines · 127 tokens per session scan A 070837fe6e69
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.
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…
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.
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.
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.
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.
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.