What Tablif read on switch-ai-code-reviewer's site
switch-ai-code-reviewer describes itself as: “switch-ai-code-reviewer | Agensi”
- Stage: Live, no waitlist
- How it differs: “Unlike a manual prompt, this skill uses a structured audit framework that specifically targets local diff context and known vulnerability patterns, providing more consistent and reliable results than a generic chat interaction.”
What it is
Calls itself “skill”.
- Calls itself: skill
“…switch-ai-code-reviewer | Agensi”
“…skill”
Where it puts itself
Rules out “Does this skill require my code to be pushed to a remote repository like GitHub to work? No”.
- Says it will not: Does this skill require my code to be pushed to a remote repository like GitHub to work? No
“Unlike a manual prompt, this skill uses a structured audit framework that specifically targets local diff context and known vulnerability patterns, providing more consistent and reliable results than a generic chat interaction.”
“Does this skill require my code to be pushed to a remote repository like GitHub to work? No, the tool operates on your local git diffs and staged changes”
How it runs
A bot. Runs locally and works offline. Offers an API. AI is the core of the product. Built with Google Analytics and Supabase.
- Kind: bot
- Runs where: on the device, offline
- API: yes
- AI role: core to the product
- Analytics: Google Analytics
- Auth: Supabase
“This skill is a complete MCP port of the switch-ai-code-reviewer bot. It has been refactored from a centralized webhook architecture into a secure, client-side stdio MCP server”
“This tool interfaces with local git environments and uses an MCP server running on Node.js to process code analytics.”
What it works with
Integrates with Codex CLI, Cursor, Dots and 3 more. Names Claude Code on its pages.
- Integrates with: Codex CLI · Cursor · Dots · +3
- Names: Claude Code
“Claude Code”
“Codex CLI”
What it offers as proof
Live, no waitlist. Instant signup. Publishes docs.
- Instant signup: yes
“Buy skill $6”
“Docs -> https://www.agensi.io/docs”
Sources
Tablif read these pages, last on 8 Nov 2026. Everything above is what the product says about itself; Tablif does not verify every claim.
Similar products in Tablif Town
- DiffCode: Review coding-agent changes without opening an IDE
- ReproWise: AI bug reports and UI/UX audits developers can act on
- AVP: Open source alternative to Git for AI coding agents
- anubis-guardian: Deterministic repository security for AI-assisted code
- dynos-work: Self-auditing AI coding agent that learns your codebase
- Vetoo: Low-noise AI code review that adapts to your team
- ChangeLatch: Apply AI-generated code changes without manual file edits
- Sonah: Reviews what your coding agent did, not just the diff