nexus-gateway: Skill for Claude Code

.claude/skills/run-local/SKILL.md

run-local is a skill for Claude Code from AlphaBitCore/nexus-gateway. It costs 111 tokens per session (3,096 once invoked), scanned A, original, Apache-2.0.

A startup procedure for running the complete Nexus Gateway locally from a fresh or existing code checkout. It starts the supporting databases and messaging services, the four Go services, and the Vite web interface.

In plain words
What is it for?
Use it to prepare a local development environment, start the gateway stack, check that each service is listening on its expected port, and confirm that the admin interface opens.
Why use it?
It avoids the setup mistakes that commonly prevent a first-time contributor from getting all parts of a multi-service application running together.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; positional $N argument.

This is AlphaBitCore/nexus-gateway's own configuration. It tells Claude Code how to work on nexus-gateway itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nexus-gateway configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/dev-start.sh --no-dev.

Reuse

Borrowing it

Nothing to install: this file belongs to AlphaBitCore/nexus-gateway. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/AlphaBitCore/nexus-gateway/main/.claude/skills/run-local/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/AlphaBitCore/nexus-gateway

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 run-local

README.md
[![agentmods](https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/run-local.svg)](https://agentmods.dev/skills/alphabitcore/nexus-gateway/run-local)
Your own site
<a href="https://agentmods.dev/skills/alphabitcore/nexus-gateway/run-local"><img src="https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/run-local.svg" alt="Measured on agentmods" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,096 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 14 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 18
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 85
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 179
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 180
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 191
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Excessive Agency · line 8
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 136
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium MCP Rug Pull · line 73
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium Rogue Agent · line 99
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 104
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 109
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 114
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 159
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Data Exfiltration · line 162
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 $0.00111 $0.03096
Opus 5 $0.00056 $0.01548
Sonnet 5 $0.00022 $0.00619
Haiku 4.5 $0.00011 $0.00310

Measured 7d ago against content hash 9e9a8558c8f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

run-local scanned grade A with 1 finding 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 7d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -o /dev/null -w "%{http_code}\n" http://localhost:3000/
.claude/skills/run-local/SKILL.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run Local

Goal: take a fresh clone (or a dirty workspace) of Nexus Gateway and end with 5 services listening on the documented ports, ready for an admin login at http://localhost:3000. Every step has a guard so the model can self-heal rather than hand back to the user.

This skill is the user-facing complement to scripts/dev-start.sh: the script handles the Docker / DB / .env bootstrap; this skill drives the rest (start the four Go services with the right flags, verify each one, surface the few errors that need user input).

Goal first, plan second (binding pattern)

Before any tool call, restate to the user in one line: "Goal: bring up the 5 local services. Plan: bootstrap → start Hub → CP → AI GW → Proxy → UI, verify each port, smoke health." If the user adds a constraint mid-stream (different branch / dirty DB / wants to keep current data), re-anchor the goal and continue.

Required ports (free these before starting)

Port Service Listen evidence on macOS lsof
3000 Control Plane UI (Vite) node … TCP *:hbci (LISTEN)
3001 Control Plane (Echo) control-p … TCP *:redwood-broker (LISTEN)
3040 Compliance Proxy complianc … TCP localhost:tomato-springs (LISTEN)
3050 AI Gateway ai-gatewa … TCP *:gds_db (LISTEN)
3060 Nexus Hub nexus-hub … TCP *:interserver (LISTEN)
55532 PostgreSQL (Docker) com.docker … LISTEN
6437 Valkey (Docker) com.docker … LISTEN
4222 / 8222 NATS (Docker) com.docker … LISTEN

macOS lsof prints IANA service names (hbci, redwood-broker, …) instead of port numbers — they are the same port, no aliasing.

Step 0 — Parallel-instance check (must run first)

A common first-run failure: the user has another local checkout running services that share this Docker Postgres. Symptoms: metric_ops_raw table fills with rows referencing thing IDs that don't exist (FK violation on prisma db push).

ps aux | grep -E "nexus-hub|control-plane|ai-gateway|compliance-proxy" | grep -v grep
lsof -i :3001 -i :3040 -i :3050 -i :3060 2>/dev/null | grep LISTEN

Read the full file on GitHub · 228 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. 7d ago First seen · 228 lines · 111 tokens per session scan A 9e9a8558c8f9

Subscribe to this mod's changes

run-local is a skill published in the GitHub repository AlphaBitCore/nexus-gateway (23 stars, last pushed 5d ago), licensed Apache-2.0. It adds 111 tokens to every session and 3,096 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.