balsm-health

balsm-health/Balsm-AI

Plugin Claude Code

Shared AI skills, slash commands, and subagents for all Balsm repos.

balsm-health/Balsm-AI

Instructions file CodexOpenCode

AGENTS.md instructions for balsm-health/Balsm-AI, covering balsm — agent instructions, balsm workspace, cross-repo rule, security posture and skills — on-demand index.

balsm-health/Balsm-AI

Plugin Claude Code

Balsm shared AI toolkit: skills, slash commands, subagents, bundled MCP servers (GitHub, Sentry, Supabase), and hooks (AI-governance trigger + docs-with-code commit guard), used across every Balsm repo (API, Flutter app, website, OpenWA, docs).

balsm-health/Balsm-AI

MCP server Claude CodeCodexCursor

GitHub's hosted MCP server: lets the agent search code, read and create issues and pull requests. Remote server at api.githubcopilot.com.

balsm-health/Balsm-AI

MCP server Claude CodeCodexCursor

Sentry's hosted MCP server: lets the agent search and read issues, errors and traces. Remote server at mcp.sentry.dev.

balsm-health/Balsm-AI

MCP server Claude CodeCodexCursor

Supabase's hosted MCP server: lets the agent manage projects, tables, SQL and migrations. Remote server at mcp.supabase.com.

balsm-health/Balsm-AI

Agent

Reviews changes across any Balsm repo for correctness, security, and cross-repo contract drift (API ↔ Flutter ↔ website). Read-only. Spawn for "review my Balsm change" or "check this against the API contract".

balsm-health/Balsm-AI

Command

Summarize which Balsm repo you're in and its role in the wider workspace.

balsm-health/Balsm-AI

Hook

Runs when you submit a prompt, before the agent sees it, executing ai-governance-trigger.sh. From balsm-health/Balsm-AI.

balsm-health/Balsm-AI

Hook

Runs before the agent uses a tool for Bash tool calls, executing docs-with-code-guard.sh. From balsm-health/Balsm-AI.

balsm-health/Balsm-AI

Skill Claude CodeCodex

Perform static analysis of Android APK malware samples using apktool for decompilation, jadx for Java source recovery, and androguard for permission analysis, manifest inspection, and suspicious API call detection.

balsm-health/Balsm-AI

Skill Claude CodeCodex

Parse and analyze email headers to trace the origin of phishing emails, verify sender authenticity, and identify spoofing through SPF, DKIM, and DMARC validation.

balsm-health/Balsm-AI

Skill Claude CodeCodex

Analyzes indicators of compromise (IOCs) including IP addresses, domains, file hashes, URLs, and email artifacts to determine maliciousness confidence, campaign attribution, and blocking priority. Use when triaging IOCs from phishing emails, security alerts, or external threat feeds; enriching raw IOCs with…

balsm-health/Balsm-AI

Skill Claude CodeCodex

Runtime iOS app security testing with Objection (Frida): inspect keychain and filesystem data, explore app internals at runtime, and validate/bypass client-side protections during authorized mobile assessments.

balsm-health/Balsm-AI

Skill Claude CodeCodex

Parses Kubernetes API server audit logs (JSON lines) to detect exec-into-pod, secret access, RBAC modifications, privileged pod creation, and anonymous API access. Builds threat detection rules from audit event patterns. Use when investigating Kubernetes cluster compromise or building k8s-specific SIEM detection rules.

balsm-health/Balsm-AI

Skill Claude CodeCodex

Examine Linux system artifacts including auth logs, cron jobs, shell history, and system configuration to uncover evidence of compromise or unauthorized activity.

balsm-health/Balsm-AI

Skill Claude CodeCodex

Analyzes RAM memory dumps from compromised systems using the Volatility framework to identify malicious processes, injected code, network connections, loaded modules, and extracted credentials. Supports Windows, Linux, and macOS memory forensics. Activates for requests involving memory forensics, RAM analysis…

balsm-health/Balsm-AI

Skill Claude CodeCodex

Balsm's mandatory AI governance rules for ANY AI/LLM/ML feature in the healthcare platform. Load BEFORE designing, planning, or implementing anything AI: clinical decision support (CDSS), AI chat / chatbot / copilot / assistant, ambient scribing, summarization, triage, recommendations, or any LLM/ML integration.…

balsm-health/Balsm-AI

Skill Claude CodeCodex

Use this skill to generate well-branded interfaces and assets for Balsm.health (بلسم) — the community-owned healthcare OS for the Arab world. Includes the official five-petal flower mark, the five-color petal palette, cool navy-slate neutrals, type system (Montserrat / IBM Plex Sans / IBM Plex Sans Arabic / Cairo /…

balsm-health/Balsm-AI

Skill Claude CodeCodex

Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional…

balsm-health/Balsm-AI

Skill Claude CodeCodex

Responds to security incidents in cloud environments (AWS, Azure, GCP) by performing identity-based containment, cloud-native log analysis, resource isolation, and forensic evidence acquisition adapted for ephemeral cloud infrastructure. Activates for requests involving cloud incident response, AWS security incident…

balsm-health/Balsm-AI

Skill Claude CodeCodex

The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.

balsm-health/Balsm-AI

Skill Claude CodeCodex

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

balsm-health/Balsm-AI

Skill Claude CodeCodex

Container escape is a critical attack technique where an adversary breaks out of container isolation to access the host system or other containers. Detection involves monitoring for escape indicators.