Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/ragavrida/agentsmcp/cursornpx skills add RagavRida/agentsmcp --skill cursorgit clone --depth 1 https://github.com/RagavRida/agentsmcpWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00068 | $0.00947 |
| Opus 5 | $0.00034 | $0.00474 |
| Sonnet 5 | $0.00014 | $0.00189 |
| Haiku 4.5 | $0.00007 | $0.00095 |
Grade A, and why
agentmailbox-cursor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentMailbox — Context Sync for Cursor
Your context follows you. Not the tool.
AgentMailbox gives Cursor persistent memory across Composer sessions, tools, and restarts. When a session starts, check your mailbox and pick up exactly where the last session left off — including context from Claude Desktop, Antigravity, Continue, or any other MCP-aware tool.
Setup in Cursor
1. Add MCP Server
Go to Cursor Settings → MCP and add:
{
"mcpServers": {
"agentsmcp": {
"command": "npx",
"args": ["-y", "agentsmcp-adapter"],
"env": {
"AGENTSMCP_AGENT_ID": "cursor@local",
"AGENTSMCP_SERVER": "http://localhost:3000"
}
}
}
}
For the public demo server (no self-hosting required):
{
"env": {
"AGENTSMCP_SERVER": "https://hdnxa5c8yr.us-east-1.awsapprunner.com"
}
}
2. Install Rules (Optional)
Copy the rules file to your project for always-on context sync:
mkdir -p .cursor/rules
cp skills/cursor/rules/agentmailbox.mdc .cursor/rules/
3. Start the Server (Self-Hosted)
npx agentsmcp-server
Workflows for Cursor
Session Start — Restore Context
When opening a project or starting a new Composer session:
Tool: agentsmcp_receive
This returns the full context frame:
- snapshot — Last sender's state
- threadSummaryStructured — Decisions, open questions, artifacts from the thread
- recentMessages — Last 10 messages verbatim
Summarize for the user: "You were working on [X]. Open questions: [Y]."
Composer Multi-File Edits
Before starting a multi-file edit in Composer, sync the relevant thread:
Tool: agentsmcp_sync
Arguments: { "threadId": "<thread-id>" }
After completing the edit, record what changed:
Tool: agentsmcp_send
Arguments:
to: "cursor@local"
body: {
"composerEdit": "Refactored auth module",
"filesChanged": ["src/auth.ts", "src/middleware.ts", "tests/auth.test.ts"],
"decisions": ["Using JWT with 24h expiry", "Middleware validates on every route"],
"status": "complete"
}
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 139 lines · 68 tokens per session scan A 1df1bcb5337a
agentmailbox-cursor is a skill published in the GitHub repository RagavRida/agentsmcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 947 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
create-release
Create releases with proper versioning, release notes, and Git tags.
deploy-agent
Deploy Bindu agents to various environments with safety checks and verification.
add-example-agent
Add a new self-contained example agent under examples/. Use when asked to "create an example for ", "add a tutorial agent", "demo integration with ", or when showcasing a new pattern users should copy.
debug-grpc-connection
Diagnose gRPC connection issues between the Bindu core and a language SDK. Use when an SDK fails to register, HandleMessages calls time out, "connection refused" on :3774, heartbeats stop arriving, or the core logs "agent silently died".
test-pr
Test pull requests with comprehensive validation and generate structured test results.
question-answering
General-purpose question answering capability powered by OpenRouter. Access 300+ LLM models (GPT-4o, Claude, Llama, Gemini, Mistral, etc.) through a single unified API. Handles conversational queries, explanations, code generation, analysis, and creative writing.