nac

Skill Productivity Usable

Works inClaude Code

Usable Scanned — metadata only

Long-running AI agent tasks often drift from intent or fail mid-execution.

Give AI agents ambitious work without losing the plot. nac is an open-source harness for long-running tasks, using a central orchestrator, threads, and structured episodes to stay aligned with your intent.

Orchestrate multi-step data pipeline tasks that span hours without losing track of progress
Break down complex research projects into structured episodes with clear checkpoints and validation
Manage parallel agent workflows that coordinate across multiple threads while maintaining alignment

261 starsApache-2.0 (commercial OK)FreeQuick setup

Usable rating — This tool is functional but has notable gaps. Review the evaluation notes below before deploying.

Why it matters

Long-running AI agent tasks often drift from intent or fail mid-execution. nac provides structured episode management and orchestration to maintain coherence across complex, multi-step workflows while reducing abandonment and re-work cycles.

Best for

Engineering teams deploying multi-step AI agents for sustained automation tasks requiring reliable state management and intent tracking.

Works in

Claude Code Claude Cowork Claude Chat

Source

https://github.com/arcee-ai/nac

By arcee-ai

How to Get It

Option 1: Claude Desktop App (Code Mode)Click the + button next to the prompt box → Plugins → Add plugin. Search and click Install. Skills work in Claude Code only.

Option 2: Paste into Claude CodeCopy the command below and paste it into your conversation. Claude will install it.

Command

claude plugins install arcee-ai/nac

Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.

Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.

First thing to try

After installing, paste this into Claude:

Help me orchestrate multi-step data pipeline tasks that span hours without losing track of progress

CostFree

Trust Signals Auto-scanned

Stars261Contributors8Last updated2026-09-12LicenseApache-2.0 (OK for commercial use)Known CVEsNone foundSources: GitHub Advisory Database + OSV.dev · Scanned 2026-09-19 · scanner v1

Reviewer notes

Auto-scanned review. These are observations, not a security certification.

Scored from trust signals (evidence-eval-v1): 234 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.

Things to check

Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.

How to evaluate tools before deploying →

Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.

Evaluation Scores

Evaluation

Ease of Use

3/5

Versatility

3/5

Reliability

3/5

Security

3/5

Overall score3.00 / 5.00 UsableEvaluatedSep 2026

Scored from trust signals (evidence-eval-v1): 234 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.

← Back to the Claude Observatory