nw-collaboration-and-handoffs

nw-collaboration-and-handoffs is a skill for Claude Code from nWave-ai/nWave. It costs 32 tokens per session (903 once invoked), scanned A, original, MIT.

A set of rules for coordinating work between coding agents, including what information to pass between stages and how to hand off TDD, refactoring, and architecture work. TDD means writing tests around the expected behavior before or alongside implementation.

In plain words
What is it for?
Use it when transferring work between agents, moving from design to implementation, switching from TDD to architectural refactoring, or preparing a completed change for delivery.
Why use it?
It keeps multi-step engineering work understandable when different agents handle design, testing, implementation, and delivery. Clear handoffs reduce lost context and make the next stage’s responsibilities explicit.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit Use it when transferring work between agents, moving from design to implementation, switching from TDD to architectural refactoring, or preparing a completed change for delivery.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nwave-ai/nwave/nw-collaboration-and-handoffs
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 nWave-ai/nWave --skill nw-collaboration-and-handoffs
Clone the repo
git clone --depth 1 https://github.com/nWave-ai/nWave

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.

agentmods badge for nw-collaboration-and-handoffs

README.md
[![agentmods](https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-collaboration-and-handoffs/github.svg)](https://agentmods.dev/skills/nwave-ai/nwave/nw-collaboration-and-handoffs)
Your own site
<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-collaboration-and-handoffs"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-collaboration-and-handoffs/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 nw-collaboration-and-handoffs

Your own site · 80×15
<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-collaboration-and-handoffs"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-collaboration-and-handoffs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 903 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00032 $0.00903
Opus 5 $0.00016 $0.00451
Sonnet 5 $0.00006 $0.00181
Haiku 4.5 $0.00003 $0.00090

Measured 11d ago against content hash 82002c83dc6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

nw-collaboration-and-handoffs 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 11d 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.

nWave/skills/nw-collaboration-and-handoffs/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Collaboration and Handoffs

Cross-Agent Collaboration

Receives From

  • acceptance_designer (DISTILL): E2E acceptance tests | business validation requirements | production integration patterns
  • solution_architect (DESIGN): architecture patterns | component boundaries | technology constraints | port definitions

Hands Off To

  • feature_completion_coordinator (DELIVER): working implementation | complete test coverage | quality metrics | refactored codebase | validated business value

Collaborates With

  • architecture_diagram_manager: visual validation of implementation against architecture | diagram updates during refactoring

4 Workflow Handoff Patterns

1. TDD to Mikado

  • Trigger: complex architectural refactoring requirements emerge during TDD
  • Content: working implementation with test coverage | identified architectural complexity | business value articulation
  • Transition: Pause TDD at stable green state -> Activate Mikado exploration -> Define business-value-focused refactoring goal -> Execute exhaustive exploration with discovery-tracking commits -> Build complete dependency tree -> Resume through Mikado execution or transition to refactoring

2. TDD to Refactoring

  • Trigger: feature implementation complete, code quality improvements needed
  • Content: working implementation with test coverage | code smells identified | all tests passing
  • Transition: Commit TDD implementation (all tests green) -> Activate progressive refactoring -> Execute comprehensive code smell detection -> Apply Level 1-6 refactoring in mandatory sequence -> Maintain 100% test pass rate throughout -> Commit after each successful atomic transformation

3. Mikado to Systematic Execution

  • Trigger: Mikado exploration complete, true leaves identified
  • Content: complete dependency tree with annotations | true leaves with zero prerequisites | refactoring mechanics per node
  • Transition: Validate exploration completeness -> Confirm tree structure with proper nesting -> Activate systematic execution -> Execute leaves bottom-up using embedded refactoring knowledge -> Maintain shared progress tracking -> Ensure test-driven safety throughout

Read the full file on GitHub · 102 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. 11d ago First seen · 102 lines · 32 tokens per session scan A 82002c83dc6c

Subscribe to this mod's changes

nw-collaboration-and-handoffs is a skill published in the GitHub repository nWave-ai/nWave (610 stars, last pushed 5d ago), licensed MIT. It adds 32 tokens to every session and 903 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 2026-08-30.