romainsantoli-web

Agent-to-Agent (A2A) Protocol RC v1.0 bridge for OpenClaw agents. Enables agent discovery, identity cards, task lifecycle management, push notification configuration, task cancellation, and SSE subscriptions compliant with the A2A RC v1.0 specification. Covers gaps G1-G8 from the Phase 7 disruption roadmap.

Haute disponibilité du bridge ACP et gestion des sessions agents autonomes. Comble les gaps C4 (ACP sans persistance), H3 (sessions spawn sans provider env), H4 (cron bloqué en sandbox), et H5 (race condition workspace) dans openclaw/openclaw.

Advanced security audit pack covering secrets lifecycle, path canonicalization, exec plan freeze, hook routing, config includes, prototype pollution, safeBins profiles, and group policy defaults. 8 deep security tools.

Multi-agent task orchestration pack. DAG-based parallel task execution and team status monitoring. 2 orchestration tools.

Authentication and compliance audit pack. OAuth 2.1/OIDC Discovery, token scope enforcement, tool deprecation lifecycle, circuit breaker, GDPR residency, DID identity, model routing, and resource links. 8 compliance tools.

Browser automation security audit pack. Validates Playwright/Puppeteer headless configuration for dangerous arguments. 1 audit tool.

Configuration migration and integrity audit pack. Shell env sanitization, plugin integrity, token separation, OTEL redaction, and RPC rate limiting. 5 migration tools.

Post-processing skill for firm-orchestration: converts the structured JSON output of a multi-agent workflow run into real deliverables — GitHub Pull Requests, Jira/Linear tickets, Markdown reports, project briefs or structured documents. Acts as the last-mile bridge between agent output and team tooling.

Curated skill bundle for e-commerce platforms, D2C brands and marketplace operators. Activates the firm pyramid with Marketing, Commercial, Operations and Engineering agents pre-configured for catalog management, campaign orchestration, customer support and revenue operations workflows.

Ecosystem differentiation audit pack. MCP firewall, RAG pipeline, sandbox exec, context health, provenance tracking, cost analytics, and token budget optimization. 7 ecosystem tools.

Curated skill bundle for fintech startups, neobanks, payment processors and wealth-management platforms. Activates the firm pyramid with Finance, Legal, Engineering and Compliance agents pre-configured for AML/KYC, financial modelling, regulatory reporting and payment infrastructure workflows.

Multi-instance Gateway fleet management pack. Status monitoring, dynamic add/remove, broadcast commands, config sync, and fleet inventory. 6 fleet orchestration tools.

Gateway authentication hardening and credentials audit pack. Validates device auth, Baileys credentials, webhook HMAC signatures, log configuration, and workspace integrity. 5 specialized security tools.

Système de mémoire adaptative hebbienne pour Claude.md — transforme les logs de sessions en patterns pondérés qui renforcent ou atrophient les règles de travail selon l'usage réel. Implémente le Cahier des Charges v1.0.0 "Système de Mémoire Adaptative Hebbienne + Base Vectorielle pour Claude.md".

Internationalization audit pack. Locale file scanning and missing translation key detection. 1 i18n tool.

Curated skill bundle for law firms, legal departments and compliance teams. Activates the firm pyramid with Legal, Compliance, Privacy and Contracting agents pre-configured for document review, regulatory tracking and risk analysis.

Legal status analysis and corporate structuring pack. Legal form comparison, tax simulation, social protection analysis, governance structuring, and compliance checklist. 5 legal status tools.

Location strategy and site selection pack. Geo-economic analysis, real estate intelligence, site scoring, tax incentive optimization, and TCO simulation. 5 location tools.

Market research and competitive intelligence pack. Competitive analysis, market sizing, financial benchmarking, web research, report generation, and competitive monitoring. 6 market research tools.

Curated skill bundle for medical device companies, digital health startups and pharma R&D teams. Activates the firm pyramid with RA (Regulatory Affairs), Clinical, R&D and Quality agents pre-configured for FDA/CE compliance, clinical documentation and pharmacovigilance workflows.

Memory infrastructure audit pack. pgvector configuration validation and knowledge graph integrity check. 2 memory tools.

n8n workflow bridge pack. Export OpenClaw pipelines to n8n format and import n8n workflows. 2 bridge tools.

Observability pipeline and CI audit pack. JSONL-to-SQLite trace ingestion and CI workflow validation. 2 observability tools.

Pyramid multi-agent orchestration for OpenClaw: routes objectives from a CEO agent down through departments, services and employees via sessions_send / sessions_spawn, collects and merges results, enforces handoff contracts, and writes the final deliverable back to the originating session.

Platform alignment audit pack for OpenClaw 2026.2. Secrets v2, agent routing, voice security, trust model, autoupdate, plugin SDK, content boundaries, and sqlite-vec. 8 platform tools.

Prompt injection and jailbreak detection pack. 16 compiled regex patterns across 3 severity levels (CRITICAL, HIGH, MEDIUM). Supports single-prompt and batch scanning modes.

Reliability probing and documentation sync pack. Gateway health probing, documentation sync validation, channel audit, and ADR generation. 4 reliability tools.

Runtime environment and configuration audit pack. Validates Node.js version, secrets workflow, HTTP headers, allowed commands, trusted proxy, disk budget, and DM allowlist. 7 runtime security tools.

Curated skill bundle for SaaS companies (B2B and B2C) covering product development, go-to-market, customer success and engineering excellence. Activates the full firm pyramid with agents pre-configured for sprint planning, release management, PLG growth loops and churn analysis.

Audit de sécurité proactif des déploiements OpenClaw. Détecte et remédie aux 4 gaps critiques/hauts identifiés dans openclaw/openclaw : SQL injection (C1), sandbox off par défaut (C2), session secret éphémère (C3), absence de rate limiting (H8), et documentation sécurité incomplète (M10).

Skill lazy loading and search pack. On-demand SKILL.md loading and keyword-based skill search. 2 loader tools.

MCP 2025-11-25 specification compliance audit pack. Validates elicitation, tasks, resources/prompts, audio content, JSON Schema 2020-12, SSE transport, and icon metadata compliance. 7 specialized audit tools.

Procurement and supplier management pack. Supplier sourcing, multi-criteria evaluation, TCO analysis, contract management, and supply chain risk monitoring. 5 procurement tools.

VS Code bridge pack. Context push/pull and session linking between VS Code and OpenClaw Gateway. 4 bridge tools.