nw-continue

nw-continue is a skill for Claude Code, Codex from nWave-ai/nWave. It costs 28 tokens per session (1,127 once invoked), scanned A, original, MIT.

Detects current wave progress for a feature and resumes at the next step. Scans docs/feature/ for artifacts.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/nwave-ai/nwave/nw-continue
Any agent
npx skills add nWave-ai/nWave --skill nw-continue
Clone the repo
git clone --depth 1 https://github.com/nWave-ai/nWave

Made for: Claude Code, Codex.

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-continue

README.md
[![agentmods](https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-continue.svg)](https://agentmods.dev/skills/nwave-ai/nwave/nw-continue)
Your own site
<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-continue"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-continue.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,127 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00028 $0.01127
Opus 5 $0.00014 $0.00563
Sonnet 5 $0.00006 $0.00225
Haiku 4.5 $0.00003 $0.00113

Measured today against content hash de46e250d197, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nw-continue 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 today.

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-continue/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NW-CONTINUE: Resume a Feature

Wave: CROSS_WAVE (entry point) | Agent: Main Instance (self — wizard) | Command: /nw-continue

Overview

Scans docs/feature/ for active projects, detects wave artifacts, displays progress summary, launches next wave command. Eliminates manual artifact inspection when returning after hours/days.

You (main Claude instance) run this wizard directly. No subagent delegation.

Behavior Flow

Step 1: Scan for Projects

If project ID provided as argument, use it directly.

Otherwise scan docs/feature/ for project directories:

ls -d docs/feature/*/

No directories found: Display "No active projects found under docs/feature/." Suggest /nw-new. Stop.

Step 2: Project Selection (Multiple Projects)

If multiple directories exist, list by most recent file modification:

find docs/feature/{feature-id}/ -type f -printf '%T@ %p\n' | sort -rn | head -1

Present via AskUserQuestion: project name|last modified date|most recent first. Ask user to select.

Step 3: Wave Progress Detection

Check each wave's artifacts using Wave Detection Rules in ~/.claude/nWave/skills/common/wizard-shared-rules.md.

Step 4: Anomaly Detection

Check before showing progress:

Empty/corrupted artifacts: Verify file size > 0 for each "complete" artifact. If empty, flag: "Warning: user-stories.md exists but is empty (0 bytes). Recommend re-running DISCUSS wave."

Non-adjacent waves (skipped): If artifacts exist for non-consecutive waves (e.g., DISCUSS + DELIVER but no DESIGN/DISTILL), warn with options:

  1. Fill the gap — start from missing wave
  2. Continue as-is
  3. Show all artifacts for manual review

Step 5: DELIVER Progress Detail

If DELIVER in progress, show step-level detail:

  • Read docs/feature/{id}/deliver/execution-log.json — count COMMIT/PASS steps, find first without COMMIT/PASS
  • Read .develop-progress.json if exists: check last failure point
  • Display: "DELIVER in progress: Steps 01-01 through 02-01 complete. Next: 02-02"

Read the full file on GitHub · 127 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. today First seen · 127 lines · 28 tokens per session scan A de46e250d197

Subscribe to this mod's changes

nw-continue is a skill published in the GitHub repository nWave-ai/nWave (604 stars, last pushed 4d ago), licensed MIT. It adds 28 tokens to every session and 1,127 once invoked, about $0.0001 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 2026-09-03.