nexus-gateway: Skill for Claude Code

.claude/skills/gap-review/SKILL.md

gap-review is a skill for Claude Code from AlphaBitCore/nexus-gateway. It costs 98 tokens per session (2,921 once invoked), scanned A, original, Apache-2.0.

A comparison process that checks software design documents against requirements, API specifications, source code, and unit tests. An SDD, or software design document, describes how the system should work.

In plain words
What is it for?
Use it after large code changes or when auditing selected features to create a prioritized plan for bringing documentation, implementation, interfaces, and tests back into alignment.
Why use it?
It finds cases where the documentation no longer matches the code, or where the code does not meet the documented design.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

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 →

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/gap-review/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 gap-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/gap-review/github.svg)](https://agentmods.dev/skills/alphabitcore/nexus-gateway/gap-review)
Your own site
<a href="https://agentmods.dev/skills/alphabitcore/nexus-gateway/gap-review"><img src="https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/gap-review/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 gap-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/alphabitcore/nexus-gateway/gap-review"><img src="https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/gap-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,921 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 $0.00098 $0.02921
Opus 5 $0.00049 $0.01460
Sonnet 5 $0.00020 $0.00584
Haiku 4.5 $0.00010 $0.00292

Measured 9d ago against content hash bdfd16fefbaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

gap-review 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 9d 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.

.claude/skills/gap-review/SKILL.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gap Review — SDD-Driven Parity Audit

This skill audits the alignment between SDD documents (the source of truth) and all downstream artifacts: architecture, requirements, OpenAPI specs, code implementation, and unit tests. It identifies gaps in both directions — docs that lag behind code and code that does not fully implement the SDD — then produces a prioritized plan to fix everything.

Core principle: The SDD defines what the system should do. Code that diverges from SDD is either a doc gap (SDD needs updating to match intentional code changes) or a code gap (code is incomplete). This skill distinguishes between the two and fixes both.


Invocation Protocol

When this skill is triggered, follow these steps in order. Do not skip steps. Do not start fixing anything before the audit is complete.


Phase 1: Scope Selection

Ask the user:

  1. Which epics/stories to audit?

    • All epics (full audit)
    • Specific epic(s) (e.g., E1, E7)
    • Specific story/stories (e.g., e1-s1, e7-s4)
    • Auto-detect from recent git changes (use git log --name-only to find recently changed source files, then map them back to SDD stories)
  2. What is the priority?

    • Code gaps (code does not implement SDD) — fix code first
    • Doc gaps (docs do not reflect code) — update docs first
    • Both equally (default)

If the user says "just run it" or similar, default to: auto-detect from recent git changes, both equally.


Phase 2: SDD Inventory & Mapping

For each story in scope:

  1. Read the SDD file from docs/developers/specs/e{epic}-s{story}-{name}.md
  2. Extract structured data:
    • Story statement (As a / I want / So that)
    • All tasks (T1, T2, ...)
    • All acceptance criteria (checked and unchecked)
    • Dependencies
  3. Map to related artifacts:
Artifact Location How to find
Architecture docs/users/product/architecture.md (system overview) + per-module docs via docs/developers/architecture/README.md (e.g., hook-architecture.md, routing-architecture.md) Find the SDD area in the trigger map; open the listed module arch doc(s).
Requirements docs/developers/specs/e{epic}-*.md Match by epic number
OpenAPI spec docs/users/api/openapi/e{epic}-s{story}-*.yaml Match by epic-story
Aggregate OpenAPI docs/users/api/openapi/gateway-api.yaml Check if story endpoints are included
Code (gateway) packages/gateway/src/ Match by feature area from SDD tasks
Code (dashboard) packages/dashboard/src/ Match by feature area from SDD tasks
Unit tests packages/*/src/**/*.test.ts, packages/*/src/**/*.spec.ts Match by module under test

Read the full file on GitHub · 301 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. 9d ago First seen · 301 lines · 98 tokens per session scan A bdfd16fefbaa

Subscribe to this mod's changes

gap-review is a skill published in the GitHub repository AlphaBitCore/nexus-gateway (23 stars, last pushed 7d ago), licensed Apache-2.0. It adds 98 tokens to every session and 2,921 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

audit-expert

Expert-level security auditing, compliance, code review, and vulnerability assessment. Use when the user mentions compliance, security review, code review, vulnerability assessment, SOC 2, or GDPR, or when the task involves Audit Types, Audit Frameworks, Audit Process, or Authentication Review.

personamanagmentlayer/pcl · 60 tokens

defenseclaw-ops

Manage DefenseClaw enterprise security - scan components, manage tool permissions, view alerts, configure guardrails.

automateyournetwork/netclaw · 27 tokens

soc2-expert

Expert in SOC 2 compliance, trust service criteria, audit preparation, controls implementation, and security frameworks. Use when the user mentions compliance, audit, trust services, AICPA, controls, or security framework, or when the task involves Trust Service Criteria, SOC 2 Types, Security Common Criteria, or…

personamanagmentlayer/pcl · 71 tokens

mariana-audit

Full-depth audit (a11y, UX, perf, SEO, security, DB, architecture, legal compliance, ops, observability) of a project. Audits by reading the source directly — installs nothing, writes nothing outside docs/audits/. Reports findings with file:line evidence and calibrated severity, optionally mitigates as discovered. Use…

ibaifernandez/mariana-audit · 111 tokens

audit

A guide to Linux security auditing, which records selected system and user actions for investigation and compliance checks. It uses auditd, Linux's system auditing service.

chaterm/terminal-skills · 5 tokens

ai-identity-platform

Structured identity management for AI agent fleets — define, govern, and audit agent personas at scale.

live-neon/persona-mcp · 23 tokens