A handoff workflow that gives a tested software specification and its behavior files to an implementer such as Claude Code, Cursor, Copilot, or a developer. It collects the implementer's code changes and can optionally check each increment with an independent verifier.

Use it to package a grounded specification for another implementer, receive the resulting code diff, and optionally verify the build step by step.

It separates deciding what should be built from writing production code. This makes the requested behavior explicit and can catch problems during implementation when verification is enabled.

delegate — Skill for Claude Code by NVZver

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.

Any agent

npx skills add NVZver/claude-marketplace --skill delegate

Clone the repo

git clone --depth 1 https://github.com/NVZver/claude-marketplace

Made for: Claude Code.

Or install lsa, the plugin that ships this one along with the rest of its 7 skills, 1 agent, 1 hook.

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/skills/nvzver/claude-marketplace/delegate/github.svg)](https://agentmods.dev/skills/nvzver/claude-marketplace/delegate)

Your own site

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

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,888 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.

Model	Per session	Once invoked
Fable 5.1	$0.00045	$0.01888
Opus 5	$0.00023	$0.00944
Sonnet 5	$0.00009	$0.00378
Haiku 4.5	$0.00005	$0.00189

Measured 8d ago against content hash 441aa4bb198a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

delegate 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 8d 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/skills/delegate/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trace. On load, print first: =============== [lsa/skills/delegate/SKILL.md] [lsa] ===============

LSA Delegate

See CORE.md. The handoff boundary — LSA writes no production code.

Role

Handoff.

Goal

Get a grounded spec built by the implementer the developer already uses, and collect the result. When paired_verify: checkpoint is set, gate the build increment-by-increment via an independent verifier without ever writing code itself.

Inputs

Input	Source
The grounded spec + `<flow>.feature` files	`verify` (GROUNDED)
The chosen implementer (Claude Code / Cursor / Copilot / human)	`user`
`.lsa.yaml paired_verify` (`off` \| `checkpoint` \| `async`; default `off`)	`.lsa.yaml` (per `../../knowledge/conventions.md` Read protocol)

Steps

Read the paired-verify mode. Read .lsa.yaml paired_verify (per the conventions Read protocol). Absent ⇒ off. Values: off | checkpoint | async; schema in ../../ARCHITECTURE.md §3. Observable result: the mode is named back to the human. (→ mode)
Package the spec + .feature files as repo files — the self-contained handoff. (→ handoff)
Branch on the mode:
- off (default / absent) — unchanged delegation (G2). Dispatch to the developer's implementer (this runs outside LSA), then await the returned diff. Inject no pause instruction and dispatch no verifier — byte-for-byte today's behavior. The implementer is a floored routing surface (lsa:delegate — never resolves below inherit; code quality is load-bearing) per ../../knowledge/model-routing.md. Skip to Step 6. (→ delegated → diff)
- async — refuse, do not degrade (G3). ERROR: async (concurrent-interrupt model) is not yet implemented — reserved for a later pitch. Do not fall back to checkpoint or off; do not dispatch. Stop here — no silent degradation.

Read the full file on GitHub · 83 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.

8d ago First seen · 83 lines · 45 tokens per session scan A 441aa4bb198a

Subscribe to this mod's changes

delegate is a skill published in the GitHub repository NVZver/claude-marketplace (1 stars, last pushed 14d ago), licensed MIT. It adds 45 tokens to every session and 1,888 once invoked, about $0.0002 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.

Building agents Claude Code ai-agents claude-code-marketplace claude-code-plugin prompt-engineering spec-driven-development

top-design

Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…

wondelai/skills · 113 tokens

traction-eos

Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…

wondelai/skills · 147 tokens

create-app

Guided journey from a raw app idea to a validated, cleanly architected first version that ships on a sustainable cadence. Orchestrates ten skills phase by phase - lean-startup, design-sprint, clean-architecture, domain-driven-design, clean-code, pragmatic-programmer, system-design, ios-hig-design, 37signals-way…

wondelai/skills · 217 tokens

cold-start-problem

Start and scale networked products using Andrew Chen's "The Cold Start Problem" framework for network effects. Use when the user mentions "network effects", "chicken and egg", "cold start", "two-sided marketplace", "atomic network", "hard side", "liquidity", "critical mass", "invite-only launch", "how do I get my…

wondelai/skills · 168 tokens

clean-architecture

Structure software around the Dependency Rule: source code dependencies point inward from frameworks to use cases to entities. Use when the user mentions "architecture layers", "dependency rule", "ports and adapters (hexagonal)", "onion architecture", "screaming architecture", "where should business logic go"…