More screenshots
Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+21 moreClaude CodeCursorCodex CLIMuseDots
Manus
Grok
Grok Bot+18 agentsInline Comment
Best way to steer your agents, effortlessly.
$9.99
inline-comment
Example session with this skill installed
I need to review /src/auth.ts to ensure our password handling is secure. Open it so I can leave some inline feedback.
- Read your context and instructions
- Compiled the inline-comment
{
"status": "submitted",
"file": "/src/auth.ts",
"comments": [
{
"from": 22,
"to": 22,
"fromCol": 5,
"toCol": 12,
"text": "Change this to a secure hash",
"code": "md5(pw)"
}
]
}
Connects securely to your tools. The creator never sees your data.
About this skill
Precise Inline Feedback for AI Collaboration
Save tokens and supercharge your productivity by leaving anchored feedback directly on the text. Instead of copying snippets or citing line numbers in chat, point to the exact spot — the AI receives your instructions mapped precisely to the selection.
How it works
When triggered, the skill launches a lightweight editor with syntax highlighting and folding in your browser. You can select lines or specific code spans to leave comments. Once you hit submit, the AI receives a structured JSON object containing your instructions mapped precisely to the selection.
- Reference Precision: Pinpoint the exact spot you want to instruct on.
- Rich Visualization: Supports syntax highlighting for 80+ languages and renders Markdown, KaTeX math, and Mermaid diagrams.
- Easy Navigation: Folding lets you collapse and navigate long files quickly.
- Mobile-Friendly: Touch-sized hit targets and a responsive layout — review from your phone or tablet.
- Remote-Friendly: Works over SSH port forwarding or HTTP tunnels — review files on a remote machine without leaving your local browser.
- Resilient Sessions: Drafts are auto-saved locally, so you won't lose your review if you accidentally close the tab.
Supported formats
Works with virtually all source code (Python, JS, Rust, Go, etc.), configuration files (YAML, JSON, Dockerfile), and documentation (Markdown, LaTeX).
- Requires absolute file paths.
- Read-only view; users cannot edit file content directly.
- Port 8100 must be available or manually reassigned.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
4 uses
Times used to date
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 16 days ago
- Software
Python
Permissions
Terminal - For running the local server to serve the UI for user. Read Files - Read the file user need to review. Write Files - Write to <project-root>/tmp (or user specified) folder for persistence of comments. Network Access - LAN only, for serving the UI for user.