buildable-review

buildable-review is a command for Claude Code, Cursor from jj-jamen/buildable-plugin-skills. It costs 0 tokens per session (209 once invoked), scanned A, a copy of buildable-review, MIT.

A review command for Buildable prototypes, checking them against their app specification and rules for keeping work local where required. It can also run type checks and a production build when dependencies are available.

In plain words
What is it for?
Use it to audit a generated app, read its review report, fix blocking issues, and summarize what remains before shipping.
Why use it?
It identifies missing features, unintended hosted services, and build problems before the prototype is treated as ready.

Command for Claude CodeCursor

Written for Claude Code and Cursor: shipped in a Claude Code plugin, but also installed under .cursor/.

Part of the buildable plugin — 3 skills, 6 commands, 1 MCP server shipped together

Good fit Use it to audit a generated app, read its review report, fix blocking issues, and summarize what remains before shipping.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jj-jamen/buildable-plugin-skills/buildable-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.

Clone the repo
git clone --depth 1 https://github.com/jj-jamen/buildable-plugin-skills

Made for: Claude Code, Cursor.

Or install buildable, the plugin that ships this one along with the rest of its 3 skills, 6 commands, 1 MCP server.

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 buildable-review

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/jj-jamen/buildable-plugin-skills/buildable-review"><img src="https://agentmods.dev/badge/commands/jj-jamen/buildable-plugin-skills/buildable-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 209 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 100% copy Near-identical to another mod 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 $0.00000 $0.00209
Opus 5 $0.00000 $0.00105
Sonnet 5 $0.00000 $0.00042
Haiku 4.5 $0.00000 $0.00021

Measured 9d ago against content hash e1b05355f934, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

buildable-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 9d 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.

Origin

This is a copy

100% identical to buildable-review — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursor/commands/buildable-review.md · 12 lines

What it actually says

Buildable Review

Audit a generated prototype against its Buildable app spec and local-first guardrails.

Run from the app workspace (add --build to also run typecheck/build when deps are installed):

buildable review 2>/dev/null || node "${BUILDABLE_ROOT:?Set BUILDABLE_ROOT to your Buildable checkout}/bin/buildable.mjs" review

If buildable is not globally linked, set BUILDABLE_ROOT to the local Buildable checkout. Pass a path only when reviewing another folder. Read .buildable/review-report.md, load only files named by reported issues, and fix blocking issues first (missing entities/features, hosted-feature drift, build failures) then polish. Relay the advisory Readiness section (mocked data, mock/no auth, no deploy) as the honest "what's left to ship" summary — guidance only; do not auto-add a backend or auth provider unless the user asks. Report what changed and whether the review now passes.

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. 9d ago First seen · 12 lines · 0 tokens per session scan A e1b05355f934

Subscribe to this mod's changes

buildable-review is a command published in the GitHub repository jj-jamen/buildable-plugin-skills (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 209 tokens. A static security scan graded it A with 0 findings. It is 100% identical to buildable-review, differing in 0 lines, and is treated as a copy.