nelson

Nelson is a Claude Code skill/plugin that provides a structured, risk-tiered orchestration framework for coordinating multi-agent coding sessions. It defines “sailing orders,” forms a squadron of roles (admiral/captains/red-cell), runs tasks via checkpoints (“quarterdeck rhythm”), enforces risk-tier controls (“action stations”), and produces auditable decision logs (“captain’s log”) plus recovery procedures (“damage control”).

Evaluated Mar 30, 2026 (23d ago)
Repo ↗ Ai Ml ai-agents agent-coordination claude-code claude-code-skill risk-management orchestration developer-tools
⚙ Agent Friendliness
51
/ 100
Can an agent use this?
🔒 Security
32
/ 100
Is it safe for agents?
⚡ Reliability
38
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
0
Documentation
70
Error Messages
0
Auth Simplicity
90
Rate Limits
10

🔒 Security

TLS Enforcement
0
Auth Strength
50
Scope Granularity
0
Dep. Hygiene
50
Secret Handling
60

No direct security implementation details (TLS, secret storage, dependency list, CVE posture) are present in the supplied content. Nelson emphasizes auditability, risk tiers, and verification gates; however, it operates inside Claude Code and therefore inherits the host environment’s security model. No mention of data residency or compliance controls.

⚡ Reliability

Uptime/SLA
0
Version Stability
40
Breaking Changes
40
Error Recovery
70
AF Security Reliability

Best When

You need repeatable, audit-friendly coordination across multiple agents/workstreams for non-trivial codebase changes, especially when you want risk tiers and recovery procedures.

Avoid When

You only need sequential work for a small, low-risk change and would prefer minimal ceremony.

Use Cases

  • Coordinating multi-file, multi-module Claude Code work in parallel with explicit ownership and checkpoints
  • Risk-tiered quality gates for changes with varying blast radius
  • Producing auditable decision logs and mission artifacts for later review
  • Implementing recovery/damage-control workflows for stuck agents, context exhaustion, faulty output, and partial rollback
  • Template-driven mission execution (sailing orders, battle plans, turnover briefs, decision logs)

Not For

  • One-off, quick edits in a single file where orchestration overhead is unnecessary
  • Use as a standalone API/service outside the Claude Code/Claude Code skill/plugin environment

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
No
SDK
No
Webhooks
No

Authentication

Methods: Relies on Claude Code CLI authentication (per Claude Code prerequisites)
OAuth: No Scopes: No

Authentication appears to be handled by the Claude Code CLI environment rather than by Nelson itself (no separate API auth described).

Pricing

Free tier: No
Requires CC: No

No pricing details for Nelson are provided in the supplied content. It may incur Claude Code usage costs depending on how Claude is configured, but that is not specified here.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Requires Claude Code setup; full experience depends on agent teams being enabled (ENV flag/settings.json).
  • Plugin installs are cached snapshots and may not auto-update; users must refresh marketplace cache to pick up changes.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for nelson.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered