A workflow for writing and checking software specifications before and after someone else implements them. It uses plain-language requirements, user flows, and example-based test scenarios.

Use it to inspect a codebase, turn intent into requirements and test scenarios, prepare work for a coding agent or human, and compare the finished changes with the specification.

It reduces misunderstandings between a request, its written specification, and the resulting code. It also helps identify when the implementation has drifted from the agreed requirements.

lsa — Plugin for Claude Code by NVZver/claude-marketplace

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/NVZver/claude-marketplace

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/nvzver/claude-marketplace/lsa/github.svg)](https://agentmods.dev/plugins/nvzver/claude-marketplace/lsa)

Your own site

<a href="https://agentmods.dev/plugins/nvzver/claude-marketplace/lsa"><img src="https://agentmods.dev/badge/plugins/nvzver/claude-marketplace/lsa/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/nvzver/claude-marketplace/lsa"><img src="https://agentmods.dev/badge/plugins/nvzver/claude-marketplace/lsa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 7 skills, 1 agent, 1 hook cost 333 tokens a session between them.

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.

Security

Grade A, and why

lsa 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 1mo 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.

lsa/.claude-plugin/plugin.json · 12 lines

What it actually says

{
  "name": "lsa",
  "description": "Living Spec Architecture — a technology-agnostic spec layer that authors a grounded spec and verifies it before and after an external implementer builds it. LSA is NOT the implementer: any coding agent (Claude Code, Cursor) or human writes the code. Skills: discover (extract intent + gather codebase facts; the universal input-resolver), specify (EARS requirements + user flows + Gherkin .feature scenarios), verify (ground the spec BEFORE delegating), delegate (hand the spec to any implementer), reconcile (run each Gherkin scenario against the diff, N=3 by default; absorb drift), init, revise-constitution. Agent: orchestrator (entry point — runs discover → specify → verify inline in one context; crosses a context boundary only at delegate, the external implementer, and reconcile, an independent grader). Standards: EARS + Gherkin (Specification by Example) — interoperable with Spec Kit / Kiro / Cursor — plus RTM (requirements traceability matrix), the lineage reconcile's conformance.md coverage table claims (practice, not IEEE 830 / ISO 29148 conformance). Every instruction follows Role/Goal/Inputs/Steps/Output — see lsa/CORE.md. Path-configurable via .lsa.yaml.",
  "version": "0.33.1",
  "author": {
    "name": "Nikita Zverev"
  },
  "dependencies": [
    "core"
  ]
}

Contents

What it installs

The manifest is a name and a version. 7 skills, 1 agent, 1 hook travel with it, and installing the plugin installs all of them — 333 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

1mo ago First seen · 12 lines scan A 02bf11d88ce5

Subscribe to this mod's changes

lsa is a plugin published in the GitHub repository NVZver/claude-marketplace (1 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Claude Code E2E testing Planning Testing ai-agents claude-code-marketplace claude-code-plugin prompt-engineering spec-driven-development

aco

Drive a live Appium session from Claude Code with the aco CLI — start/stop sessions, find elements, tap, swipe, type, screenshot, read page source, switch web contexts, and call platform mobile: extensions on iOS simulators/emulators and real devices.

tai2/aco · not measured

e2e-dashboard

Install a real-time Playwright E2E test dashboard (live SSE progress, 14 features) into any project.

FaisalNoman/playwright-skills · not measured

mobile-app-testing

Test your web app on real iOS Simulator / Android emulator sessions via tapflow, alongside your existing Playwright suite.

FaisalNoman/playwright-skills · not measured

green-gate-never-examined-the-case

A check reported clean without examining the case it exists for — "green" meant "nothing ran". Use when about to trust a gate, test or CI step you have never watched fail; when a guard is green but the bug it guards shipped anyway; when a check passes on a shallow clone, a disabled object, a malformed input or an…

wan-huiyan/claude-ecosystem-hygiene · not measured

ab-harness

Counterfactual A/B + layered-ablation harness for Claude Code setup. Measures whether your /.claude/ stack (skills, lessons, axioms, memory) plus in-repo discipline (docs/runbooks, decisions, findings) actually helps on real tasks. Binary A/B (setup-ON vs setup-OFF) and layered ablation (strip one layer at a time, ran.