sealgate-mcp
25MCP server Claude CodeCodexCursor
Sealgate gateway proxy: list governed MCP servers and review agent session and audit status. Runs locally from the @sealgate/mcp npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor
Sealgate gateway proxy: list governed MCP servers and review agent session and audit status. Runs locally from the @sealgate/mcp npm package. Needs 2 environment variables to run.
Skill Claude CodeCodex
Add a new fleet HTTP-wrapper MCP server to the Edison marketplace - scaffold servers/ /, classify each tool's ACL and lethal-trifecta legs, and validate. Use when adding or classifying a fleet connector.
Skill Claude CodeCodex
Preview an MCP-UI app (mcpserver/apps/) from fixtures in a browser with no MCP server, Gmail, OAuth, or network. Use when asked to see, screenshot, or test how an MCP App iframe renders, or to render it live in the Claude Code cloud.
Skill Claude CodeCodex
Manage files under .claude/{skills,agents,rules}/, .agents/{skills,rules}/, or .codex/agents/. Covers dual-tool Claude/Codex layout and reminds to run make sync-agent-config.
Skill Claude CodeCodex
Guide for creating a new path-scoped .claude/rules/ file with proper globs frontmatter and structure.
Skill Claude CodeCodex
Cut a new release - bump the version in pyproject.toml, tag, and push to trigger PyPI publish and MCP Registry publish via GitHub Actions. Use when the user asks to release, ship a version, bump and tag, cut a hotfix, or publish to PyPI.
Agent Claude Code
Use when the folder-size CI check (.github/workflows/folder-size.yaml) errors or warns, or when the user asks for help splitting a folder that has grown too many flat sibling files. Investigates the folder, interviews the user about how the area is expected to evolve, and proposes three concrete subfolder…
Agent Claude Code
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked via Task after a parent gathers diff and file contents. Loads the rubric from the thermo-nuclear-code-quality-review skill.
Hook Claude Code
Runs when a session starts on startup and resume, executing session-start.sh. From Edison-Watch/Custom-MCPs.
Settings file Claude Code
Agent settings declaring 1 hook event (SessionStart).
Skill Claude CodeCodex
Git branch hygiene - delete merged/closed branch, prune stale refs, sync dependencies.
Skill Claude CodeCodex
Instructions for running code quality checks and maintaining standards in the Python-Template project.
Skill Claude CodeCodex
Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD.
Skill Claude CodeCodex
Instructions for managing and running git hooks using prek. Use this skill for any mention of pre-commit hooks, as prek overrides pre-commit hooks.
Skill Claude CodeCodex
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
Skill Claude CodeCodex
How to use the CLI, API, and MCP interfaces. Use this skill when interacting with the tool as an end user.
Skill Claude CodeCodex
Pause execution for a requested number of minutes by sleeping one-minute increments to avoid exceeding shell timeouts.
Cursor rule Cursor
After major changes always run.
Cursor rule Cursor
Coding style rules.
Cursor rule Cursor
Please follow the following for commit message convention.
Cursor rule Cursor
How to use global config across the project.
Cursor rule Cursor
This is a reminder on deprecated modules you should be careful about.
Cursor rule Cursor
GitHub Actions doesn’t provide a default personal access token (PAT). Instead, it creates a built-in token called secrets.GITHUBTOKEN for each workflow run. This token is provided by github, and ends with the job or after 24 hrs, and the scope is limited to the current repository.
Cursor rule Cursor
Langfuse is an LLM observability tool used to monitor LLM behavior in our application. It uses decorators and callbacks to record LLM inference. Always use it in LLM-related modules to ensure traceability.