docs: update for @adversa/secureclaw npm publish and 56 audit checks

- Rename npm package from @openclaw/secureclaw to @adversa/secureclaw
- Update audit check count from 51 to 56 across all docs
- Add npm install option (Option B) to both READMEs
- Add npm badge to secureclaw/README.md
- Fix broken TOC anchor (#9-the-12-agent-rules → #9-the-15-agent-rules)
- Fix CHANGELOG v2.2.0 check count (55 → 56)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: adversa-ai

CHANGELOG.md

@@ -12,7 +12,7 @@ Seven-framework coverage. Every audit check tagged with MAESTRO layer and NIST a
 ### Audit Finding Schema Changes
 
 - `AuditFinding` type gains two optional fields: `maestroLayer` (L1-L7) and `nistCategory` (evasion/poisoning/privacy/misuse).
-- All 55 existing audit checks tagged with appropriate MAESTRO layer and NIST attack type.
+- All 56 audit checks tagged with appropriate MAESTRO layer and NIST attack type.
 - New `MaestroLayer` and `NistAttackType` type aliases exported from types.ts.
 
 ### New Audit Check

README.md

@@ -6,7 +6,7 @@ Audit, Hardening and Runtine Security for Openclaw.
 
 Developed by [Adversa AI](https://adversa.ai) -- Agentic AI Security and Red Teaming Pioneers.
 
-51 audit checks. 15 behavioral rules. 9 scripts. 4 pattern databases. 7 security frameworks mapped.
+56 audit checks. 15 behavioral rules. 9 scripts. 4 pattern databases. 7 security frameworks mapped.
 
 10/10 OWASP ASI | 10/14 MITRE ATLAS | 4/4 MITRE OpenClaw Cases | 3/3 CoSAI Principles | CSA Singapore | 6/7 CSA MAESTRO Layers | 4/4 NIST AI 100-2 GenAI Types
 
@@ -89,7 +89,7 @@ SecureClaw has two independently useful components:
 
 ### The Plugin (TypeScript)
 
-A full OpenClaw plugin with 51 audit checks, 5 hardening modules, 3 background monitors, and CLI integration. Requires Node.js 18+ and installs via `openclaw plugins install`.
+A full OpenClaw plugin with 56 audit checks, 5 hardening modules, 3 background monitors, and CLI integration. Requires Node.js 18+ and installs via `openclaw plugins install`. Available on npm as [`@adversa/secureclaw`](https://www.npmjs.com/package/@adversa/secureclaw).
 
 ### The Skill (Bash + JSON)
 
@@ -151,9 +151,16 @@ bash secureclaw/secureclaw/skill/scripts/install.sh
 
 This installs the 15 behavioral rules, 9 scripts, and 4 pattern databases to your agent's skills directory. If a workspace directory exists (`~/.openclaw/workspace/`), the installer also copies the skill there and registers it in `AGENTS.md` and `TOOLS.md` for automatic agent discovery.
 
-### Option B: Plugin from source
+### Option B: Plugin from npm
 
-For the full TypeScript plugin with 51 audit checks, background monitors, and CLI integration:
+For the full TypeScript plugin with 56 audit checks, background monitors, and CLI integration:
+
+```sh
+npm install @adversa/secureclaw
+npx openclaw plugins install -l node_modules/@adversa/secureclaw
+```
+
+### Option C: Plugin from source
 
 ```sh
 git clone https://github.com/adversa-ai/secureclaw.git
@@ -940,7 +947,7 @@ No. All audits, hardening, integrity checks, privacy checks, and supply chain sc
 
 **Can I use the skill without the plugin?**
 
-Yes. The skill (bash scripts + JSON configs + SKILL.md) is fully standalone. The plugin adds 51 audit checks, background monitoring, CLI integration, and a scoring system, but everything in the `skill/` directory works independently.
+Yes. The skill (bash scripts + JSON configs + SKILL.md) is fully standalone. The plugin adds 56 audit checks, background monitoring, CLI integration, and a scoring system, but everything in the `skill/` directory works independently.
 
 **Can I use the plugin without the skill?**
 

secureclaw/README.md

@@ -4,7 +4,9 @@ Automated security hardening for [OpenClaw](https://openclaw.ai) AI agents.
 
 Developed by [Adversa AI](https://adversa.ai) -- Agentic AI Security and Red Teaming Pioneers.
 
-51 audit checks. 15 behavioral rules. 9 scripts. 4 pattern databases. 7 security frameworks mapped.
+56 audit checks. 15 behavioral rules. 9 scripts. 4 pattern databases. 7 security frameworks mapped.
+
+[![npm](https://img.shields.io/npm/v/@adversa/secureclaw)](https://www.npmjs.com/package/@adversa/secureclaw)
 
 10/10 OWASP ASI | 10/14 MITRE ATLAS | 4/4 MITRE OpenClaw Cases | 3/3 CoSAI Principles | CSA Singapore | 6/7 CSA MAESTRO Layers | 4/4 NIST AI 100-2 GenAI Types
 
@@ -45,7 +47,7 @@ flowchart LR
 6. [Automated Hardening](#6-automated-hardening)
 7. [Scripts Reference](#7-scripts-reference)
 8. [Pattern Databases](#8-pattern-databases)
-9. [The 15 Agent Rules](#9-the-12-agent-rules)
+9. [The 15 Agent Rules](#9-the-15-agent-rules)
 10. [OWASP ASI Coverage Map](#10-owasp-asi-coverage-map)
 11. [Plugin CLI Reference](#11-plugin-cli-reference)
 12. [Configuration](#12-configuration)
@@ -140,9 +142,16 @@ bash secureclaw/secureclaw/skill/scripts/install.sh
 
 This installs the 15 behavioral rules, 9 scripts, and 4 pattern databases to your agent's skills directory. If a workspace directory exists (`~/.openclaw/workspace/`), the installer also copies the skill there and registers it in `AGENTS.md` and `TOOLS.md` for automatic agent discovery.
 
-### Option B: Plugin from source
+### Option B: Plugin from npm
+
+For the full TypeScript plugin with 56 audit checks, background monitors, and CLI integration:
+
+```sh
+npm install @adversa/secureclaw
+npx openclaw plugins install -l node_modules/@adversa/secureclaw
+```
 
-For the full TypeScript plugin with 51 audit checks, background monitors, and CLI integration:
+### Option C: Plugin from source
 
 ```sh
 git clone https://github.com/adversa-ai/secureclaw.git
@@ -869,7 +878,7 @@ No. All audits, hardening, integrity checks, privacy checks, and supply chain sc
 
 **Can I use the skill without the plugin?**
 
-Yes. The skill (bash scripts + JSON configs + SKILL.md) is fully standalone. The plugin adds 51 audit checks, background monitoring, CLI integration, and a scoring system, but everything in the `skill/` directory works independently.
+Yes. The skill (bash scripts + JSON configs + SKILL.md) is fully standalone. The plugin adds 56 audit checks, background monitoring, CLI integration, and a scoring system, but everything in the `skill/` directory works independently.
 
 **Can I use the plugin without the skill?**
 

secureclaw/package-lock.json

@@ -1,5 +1,5 @@
 {
-  "name": "@openclaw/secureclaw",
+  "name": "@adversa/secureclaw",
   "version": "2.2.0",
   "description": "Automated security hardening plugin for OpenClaw",
   "main": "dist/index.js",