# Muhammad Basit Ali

> Open-source tooling for AI agent security and cloud security: Claude Code skill packs, MCP servers and linters, threat modelling, Semgrep rules and an AI agent incident dataset.

I am Muhammad Basit Ali, a cloud security and AI agent security engineer. My day-to-day work is cloud governance: multi-account AWS guardrails, identity and endpoint controls in Microsoft 365, access reviews and the engineering teams that run them. Before that I built backend systems in Python and TypeScript, including a regulated lending platform and real-time grid software. The repositories here are the open part of that work: Claude Code skill packs, MCP servers and linters, threat modelling and static analysis for agent code, and a dataset of AI agent incidents. Each one stands alone, says what it does not do, and backs its security claims with tests.

## Claude Code skill packs

- [claude-skills](https://basitalisandhu.github.io/claude-skills/): Every skill I maintain, in one repository: 87 skills in 13 plugins from the packs below, one marketplace, one install script, synced daily.
- [aws-security-skills](https://basitalisandhu.github.io/aws-security-skills/): AWS security skills for Claude Code: account audit, SCP guardrails, blast-radius landing zones, IAM least privilege, Security Hub triage.
- [repo-engineering-skills](https://basitalisandhu.github.io/repo-engineering-skills/): Repository engineering skills for Claude Code: docs checked against the code, audits where every finding cites a line, agent context files that say only what code cannot.
- [m365-governance-skills](https://basitalisandhu.github.io/m365-governance-skills/): Microsoft 365 governance skills for Claude Code: Entra ID posture review, Intune baseline check, Graph permission preflight, Teams and group sprawl, access review pack.
- [compliance-evidence-skills](https://basitalisandhu.github.io/compliance-evidence-skills/): Compliance evidence skills for Claude Code: integrity-checked evidence packs from GitHub, AWS and Microsoft 365 exports, mapped to ISO 27001 and SOC 2, with narratives that cite evidence or say not assessable.
- [claude-dev-skills](https://basitalisandhu.github.io/claude-dev-skills/): Claude Code skills for everyday development: code review, refactoring, debugging, CI and containers, data and APIs, documentation and security basics.
- [agent-security-skills](https://basitalisandhu.github.io/agent-security-skills/): Claude Code security plugin and agent skills for securing LLM agents: threat modelling, configuration audits, prompt injection review, MCP server review, incident lookup.
- [github-manager-skills](https://basitalisandhu.github.io/github-manager-skills/): Claude Code skills for engineering managers that compute from exported GitHub data: stuck-PR and review-queue digest, iteration report, blameless postmortem timeline.
- [mac-maintenance-skills](https://basitalisandhu.github.io/mac-maintenance-skills/): Claude Code skills for cleaning up and speeding up a Mac: read-only survey first, safe tier removes only what programs recreate, leftovers and duplicate finders.

## MCP tooling

- [dev-mcp-servers](https://basitalisandhu.github.io/dev-mcp-servers/): Ten small MCP servers for everyday development and security checks.
- [mcp-server-template](https://basitalisandhu.github.io/mcp-server-template/): Secure MCP server template in TypeScript and Python, safe by default.
- [mcp-tools-lint](https://basitalisandhu.github.io/mcp-tools-lint/): Lint MCP tool schemas and annotations before clients reject them.
- [mcp-auth-doctor](https://basitalisandhu.github.io/mcp-auth-doctor/): Diagnose OAuth discovery problems on remote MCP servers.
- [mcp-egress](https://basitalisandhu.github.io/mcp-egress/): Record every host an MCP server contacts, per tool, and fail CI on new ones.
- [claude-mcp-allow](https://basitalisandhu.github.io/claude-mcp-allow/): Least-privilege Claude Code permission rules for MCP tools, generated from their annotations.
- [agentdojo-mcp](https://basitalisandhu.github.io/agentdojo-mcp/): Run AgentDojo against MCP servers.
- [mcp-rc-check](https://basitalisandhu.github.io/mcp-rc-check/): MCP specification migration checker for the 2026-07-28 revision.

## Security tooling

- [agent-threat-model](https://basitalisandhu.github.io/agent-threat-model/): Threat modeling for AI agents: describe the system in YAML, get a STRIDE and OWASP Agentic threat model.
- [agent-config-audit](https://basitalisandhu.github.io/agent-config-audit/): Audit AI agent configuration files for security risks.
- [agentic-semgrep-rules](https://basitalisandhu.github.io/agentic-semgrep-rules/): Semgrep rules for AI agent code in Python, TypeScript and JavaScript.
- [security-actions](https://basitalisandhu.github.io/security-actions/): GitHub Actions for AI agent and supply chain security checks.
- [cc-hooks](https://basitalisandhu.github.io/cc-hooks/): Typed Python SDK and offline test runner for Claude Code hooks.
- [cc-plugin-lock](https://basitalisandhu.github.io/cc-plugin-lock/): Lock file for Claude Code plugins: pins plugins and skills to content hashes and verifies them before load.
- [claude-perm-sim](https://basitalisandhu.github.io/claude-perm-sim/): Claude Code permission rule simulator: shows which rule decides a tool call and where a rule set is permissive.
- [llms-txt-gen](https://basitalisandhu.github.io/llms-txt-gen/): Generate llms.txt for any docs site or repository.
- [scp-guardrails](https://basitalisandhu.github.io/scp-guardrails/): AWS service control policy builder and linter.
- [skill-scan-gate](https://basitalisandhu.github.io/skill-scan-gate/): CI gate for Claude Code skills and plugins.
- [spotlighting](https://basitalisandhu.github.io/spotlighting/): Spotlighting for prompt injection defence in Python.

## Data and lists

- [ai-agent-incidents](https://basitalisandhu.github.io/ai-agent-incidents/): An open dataset of AI agent and LLM security incidents, with a browsable site.
- [awesome-agent-security](https://basitalisandhu.github.io/awesome-agent-security/): Curated list of AI agent security tools, papers and datasets.

## Posts

- [Four open repositories for securing AI agents, and what each is for](https://basitalisandhu.github.io/posts/four-open-repositories-for-securing-ai-agents/): A map of the open tools for AI agent security: an incident dataset, Semgrep rules for agent code, a threat-model CLI and Claude Code skill packs, with where each one stops.
- [Every Claude Code skill I maintain, in one repository](https://basitalisandhu.github.io/posts/every-claude-code-skill-in-one-repository/): 87 Claude Code skills in 13 plugins from 8 source repositories, now in one repository with one marketplace and one install script.

## Optional

- [Full text](https://basitalisandhu.github.io/llms-full.txt): every project page and post in one file
- [Feed](https://basitalisandhu.github.io/feed.xml): posts and releases as RSS