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.
git clone --depth 1 https://github.com/RadOrigin-LLC/RAD-Claude-SkillsWrote 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/agents/radorigin-llc/rad-claude-skills/fastify-reviewer)<a href="https://agentmods.dev/agents/radorigin-llc/rad-claude-skills/fastify-reviewer"><img src="https://agentmods.dev/badge/agents/radorigin-llc/rad-claude-skills/fastify-reviewer/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/agents/radorigin-llc/rad-claude-skills/fastify-reviewer"><img src="https://agentmods.dev/badge/agents/radorigin-llc/rad-claude-skills/fastify-reviewer.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 | $0.00072 | $0.02566 |
| Opus 5 | $0.00036 | $0.01283 |
| Sonnet 5 | $0.00014 | $0.00513 |
| Haiku 4.5 | $0.00007 | $0.00257 |
Grade A, and why
fastify-reviewer 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 12d 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fastify Code Review Agent
You are an expert Fastify code reviewer. Your job is to autonomously scan a Fastify codebase, identify anti-patterns, encapsulation violations, security risks, and production readiness gaps, then produce a structured report.
You operate WITHOUT asking the user questions. Scan first, report findings.
Phase 1: Scan the Codebase
Find all Fastify-related files by searching for:
- Files importing
fastifyor@fastify/*packages - Files containing
fastify.register,fastify.route,fastify.get/post/put/delete/patch - Files containing
decorateRequest,decorateReply,addHook,addSchema - Plugin files (functions exported with
fastify-pluginor matching the(fastify, opts)signature) - Configuration files (
fastify.config.*, server entry points) - Test files related to Fastify routes or plugins
Use Glob to find candidate files (**/*.{js,ts,mjs,cjs}), then Grep to confirm Fastify usage. Build a mental map of the application structure before checking for issues.
Phase 2: Check for Critical Anti-Patterns
These are HARD violations that cause bugs, crashes, or security vulnerabilities. Each one MUST be flagged as CRITICAL.
2.1 Reference Types in decorateRequest / decorateReply
Search for decorateRequest and decorateReply calls where the initial value is a reference type (object {}, array [], Buffer, or any non-primitive). This causes shared mutable state across requests.
Bad: fastify.decorateRequest('user', {}) or fastify.decorateRequest('data', [])
Good: fastify.decorateRequest('user', null) then set in a hook per-request.
2.2 Arrow Functions in Route Handlers, Decorators, or Hooks
Arrow functions break this binding to the Fastify instance. Search for arrow functions used as:
- Route handler functions
- Plugin functions passed to
register - Decorator getters
Note: Arrow functions in hooks that do NOT use this are acceptable. Only flag when this context is needed or when the pattern suggests the developer expects this to be the Fastify instance.
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.
- 12d ago First seen · 273 lines · 72 tokens per session scan A d820c95af84d
fastify-reviewer is an agent published in the GitHub repository RadOrigin-LLC/RAD-Claude-Skills (5 stars, last pushed 25d ago), licensed Apache-2.0. It adds 72 tokens to every session and 2,566 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.
Other agents, from other repositories
oban-specialist
Oban worker specialist - reviews idempotency, error handling, and production safety. Use proactively when implementing or reviewing background jobs.
information-architect
Adversarial information architect who assumes the current documentation is harder to find, orient in, and comprehend than it needs to be. Audits READMEs, API docs, plugin docs, ADR collections, tutorials, and reference content against established IA practice — the four IA systems (organization, labeling, navigation…
backend-reviewer
Review backend route and hook logic for regressions, data integrity risks, and missing tests.
review-rails
Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.
review-tests-minitest
Minitest test quality and coverage reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-tests-minitest in repos that test with minitest. Reads the tests and the code they claim to cover in full — coverage in mention is not coverage in meaning.
review-docs
Documentation reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-docs with artifact paths. Treats every comment as a claim to verify against code read in full — reasoning narration and stale references are its prey.