pdf-reader-mcp: Command for OpenCode

.opencode/command/saas-review.md

saas-review is a command for OpenCode from SylphxAI/pdf-reader-mcp. It costs 14 tokens per session (1,377 once invoked), scanned A, original, MIT.

A full review command for a SaaS product, meaning an internet-hosted software service. It examines product, engineering, security, compliance, growth, operations, and user experience together.

In plain words
What is it for?
Use it to review a web product built with the listed Next.js, tRPC, PostgreSQL, and related technologies. It is intended for an end-to-end quality and architecture review.
Why use it?
It gives one review process instead of separate, disconnected checks across a product. It also turns findings into standards, constraints, and acceptance criteria for the work.

Command for OpenCode

Written for OpenCode: installed under .opencode/. Also seen: agent in frontmatter.

This is SylphxAI/pdf-reader-mcp's own configuration. It tells OpenCode how to work on pdf-reader-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pdf-reader-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SylphxAI/pdf-reader-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/SylphxAI/pdf-reader-mcp/main/.opencode/command/saas-review.md
Clone the repo
git clone --depth 1 https://github.com/SylphxAI/pdf-reader-mcp

Made for: OpenCode.

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 saas-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/sylphxai/pdf-reader-mcp/saas-review/github.svg)](https://agentmods.dev/commands/sylphxai/pdf-reader-mcp/saas-review)
Your own site
<a href="https://agentmods.dev/commands/sylphxai/pdf-reader-mcp/saas-review"><img src="https://agentmods.dev/badge/commands/sylphxai/pdf-reader-mcp/saas-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 saas-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/sylphxai/pdf-reader-mcp/saas-review"><img src="https://agentmods.dev/badge/commands/sylphxai/pdf-reader-mcp/saas-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,377 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 $0.00014 $0.01377
Opus 5 $0.00007 $0.00688
Sonnet 5 $0.00003 $0.00275
Haiku 4.5 $0.00001 $0.00138

Measured 4d ago against content hash 9912c62fea44, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

saas-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 4d 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.

.opencode/command/saas-review.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SaaS Product Review — Master Orchestration

Mandate

  • Perform a complete end-to-end review across product, engineering, security, compliance, growth, operations, and UX.
  • Delegate work to multiple workers; you act as the final gate to improve quality.
  • Deliverables must be stated as standards, constraints, and acceptance criteria.
  • Single-pass delivery: no roadmap, no phasing, no deferrals; deliver an integrated outcome.

Non-Negotiable Engineering Principles

  • No workarounds, hacks, or TODOs.
  • Feature-first with clean architecture; designed for easy extension; no "god files".
  • Type-first, strict end-to-end correctness (DB → API → UI).
  • Serverless-first; edge-compatible where feasible without sacrificing correctness, security, or observability.
  • Mobile-first responsive design; desktop-second.
  • Precise naming; remove dead/unused code.
  • Upgrade all packages to latest stable; avoid deprecated patterns.

Fixed Platform & Stack (Locked)

Layer Technology
Platform Vercel
Framework Next.js (SSR-first)
API tRPC
i18n next-intl
Database Neon (Postgres)
ORM Drizzle
Auth better-auth
Payments Stripe
Email Resend
Observability Sentry
Analytics PostHog
Cache/Workflows Upstash Redis + Workflows + QStash
Storage Vercel Blob
Tooling Bun, Biome, Bun test
Tag Management GTM (marketing only)

Review Execution

Phase 1: All Reviews (Parallel)

Spawn all workers in parallel using the Task tool. Each worker runs its slash command and returns findings.

Delegation pattern:

Use Task tool with subagent_type: "Coder" for each worker.
Spawn ALL 8 workers in a single message (parallel execution).
Each worker prompt: "Run /{command} and return findings."
Worker Command Focus
Billing /saas-billing Stripe, webhooks, pricing governance, ledger
Auth /saas-auth SSO, passkeys, verification, sessions, account security
i18n /saas-i18n Locales, routing, canonicalization, hreflang
Platform /saas-platform Design system, SEO, PWA, performance, a11y
Security /saas-security OWASP, privacy, consent, observability, operability
Growth /saas-growth Onboarding, referral, retention, guidance
Admin /saas-admin RBAC, bootstrap, config, feature flags, ops tooling
Discovery /saas-discovery Feature opportunities, pricing optimization, competitive research

Read the full file on GitHub · 179 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. 4d ago First seen · 179 lines · 14 tokens per session scan A 9912c62fea44

Subscribe to this mod's changes

saas-review is a command published in the GitHub repository SylphxAI/pdf-reader-mcp (921 stars, last pushed 3d ago), licensed MIT. It adds 14 tokens to every session and 1,377 once invoked, about $0.0001 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 2026-09-06.