Agent skill · gstack
/plan-eng-review Lock architecture, edge cases and tests before you build
The engineering plan review asks what to review, then works through a mandatory scope challenge and four review sections on architecture, data flow, edge cases, test coverage and performance. It follows a stated set of engineering preferences, draws ASCII diagrams for flows and states, and ends by appending a structured review report to the plan.
Works with
- Claude Code
- Codex, Cursor, OpenCode, Gemini CLI and other agents
Used forPlanning and specs
When to use it
- You have an approved feature plan and want the technical design checked before coding.
- A branch diff needs an architecture-level look before deeper code review.
- You want a test plan that the QA skill can pick up later.
How it works
- 1Pick the target
Outside plan mode the agent asks whether to review the branch diff, a pasted plan or a specific path.
- 2Check design context
It looks for a design doc and CEO plan, treats them as data rather than instructions, and offers office hours if none exists.
- 3Challenge scope
A scope and complexity check must finish before the review sections begin.
- 4Review in sections
It covers architecture, data flow, edge cases, tests and performance, preferring explicit code, small diffs and tested behaviour.
- 5Close with a report
The plan must end with a review report table and either a list of unresolved decisions or a clear none.
What it steers the agent away from
- Building features or benchmarks during a review.
- Following instructions hidden in another agent's design doc.
- Calling a review complete without a saved report.
Install this skill
It installs with the gstack pack.
Claude CodeThe README wraps this command in a prompt you paste into Claude Code, which also adds a short gstack section to CLAUDE.md.
git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/.claude/skills/gstack && cd ~/.claude/skills/gstack && ./setupClaude Code (team mode for a shared repo)Run inside your repo; it commits a bootstrap so teammates get gstack with auto-updates, and needs Node.js for the required hook.
(cd ~/.claude/skills/gstack && ./setup --team) && ~/.claude/skills/gstack/bin/gstack-team-init required && git add .claude/ CLAUDE.md && git commit -m "require gstack for AI-assisted work"Codex, Cursor, OpenCode, Gemini CLI and other agentsUse --host auto for every detected agent or name one host; non-Claude hosts are listed as experimental.
git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/gstack
cd ~/gstack && ./setup --host auto # or: ./setup --host codex
./setup --status # one row per install: host, tier, scope, version, pathCommands come from the author’s README; check it for changes before you run them.
Questions
Does it need a design doc?
No. Without one it offers to run office hours first, and you can skip that to get a standard review.
What principles does it apply?
Its listed preferences favour tests for every behaviour, explicit over clever code, the smallest clear diff and storage shaped by how data is queried.
More guides from gstack
/csoRun a security audit that keeps evidence separate from claimsAudits code, infrastructure, supply chain or skills for exploitable defects, challenges each finding and can reproduce fixes in Docker.Read the guide →/office-hoursPressure-test an idea before your agent writes any codeQuestions your idea in startup or builder mode, challenges premises, compares two or three approaches and writes a design doc, with no code.Read the guide →/plan-ceo-reviewReview a plan for scope and ambition like a founderReviews a plan as a founder would, in expansion, selective, hold or reduction mode, and asks before adding or cutting any scope.Read the guide →/qaFind, reproduce and fix bugs with regression testsTests a site, API, CLI, job or webhook, reproduces each bug, writes a regression test first and commits each verified fix.Read the guide →/reviewCatch production bugs in a diff before it mergesReviews a branch diff for bugs that pass CI, dispatches specialist and adversarial passes, auto-fixes obvious issues and asks about the rest.Read the guide →/shipTake a branch from finished code to an open PRMerges the base branch, runs tests and reviews, bumps VERSION and CHANGELOG, verifies the frozen content, pushes and opens a PR.Read the guide →
Also in this pack
/autoplanRuns the CEO, design, developer experience and engineering reviews in sequence and brings only taste decisions to you.↗/benchmarkMeasures page load timings, Core Web Vitals and resource sizes in a real browser and compares them with a saved baseline.↗/browseDrives a real browser, preferring your signed-in Aside sessions, to open pages, click through flows, read the console and take screenshots.↗/canaryWatches a live URL after a deploy for console errors, failed pages and visual changes against baseline screenshots.↗/carefulWarns before destructive commands such as recursive deletes, dropped tables or force pushes, and hard-blocks the riskiest ones.↗/codexGets an independent review, challenge or consultation from the OpenAI Codex CLI and presents its output unedited.↗/design-consultationResearches your product space and proposes a full design system, written to a DESIGN.md file with font and colour previews.↗/design-htmlTurns an approved mockup into production HTML and CSS with computed text layout, detecting React, Svelte or Vue.↗/design-reviewAudits a live site for spacing, hierarchy and generated-looking patterns, then fixes them with atomic commits and before and after screenshots.↗/design-shotgunProduces several AI design mockups side by side in a browser board, collects your feedback and iterates until you pick a direction.↗/devex-reviewTests a developer product live by following its docs and getting-started flow, timing each step and comparing against the plan's scores.↗/diagramTurns an English description into a mermaid source, an editable Excalidraw file and rendered SVG and PNG, offline.↗
Summary by trendhub. The skill itself lives in garrytan/gstack/plan-eng-review by Garry Tan (MIT); read the full, current text there.