Nusantara Agent Security & Telemetry Suite
The unified defense and observability stack for autonomous AI coding agents. While individual tools solve isolated problems, the Nusantara Suite pairs Pagar's pre-execution security firewall with Prasasti's sub-millisecond telemetry engine to form an impenetrable closed-loop guardrail.
What this bundle enables:
- Pre-Execution Tool-Call Firewall: Pagar intercepts dangerous shell, SQL, and Git commands and scans outbound payloads for leaked cloud credentials (AWS, OpenAI, Anthropic, Stripe, database connection URIs) before execution.
- Blast-Radius Protection: If an agent touches undeclared files, Pagar atomically restores unauthorized modifications byte-for-byte.
- Observability & Circuit Breaking: Prasasti continuously streams agent step latencies and token usage into an in-memory columnar engine, automatically tripping circuit breakers on runaway recursive loops (LOOP_DETECTED) and budget limits (QUOTA_EXCEEDED).
Who is it for:
Developers, quantitative engineers, and enterprise teams running autonomous agents (Claude Desktop, Cursor, Antigravity, OpenHands) with access to bash, filesystem, and live terminal environments.
Both tools run in 100% pure Rust (#![forbid(unsafe_code)]) with zero external daemon dependencies and full Model Context Protocol (MCP) support. This commercial bundle includes pre-configured Enterprise Pro license keys for both Pagar and Prasasti.
Works with any agent that signs in to Agensi, such as Claude, ChatGPT, Claude Code, Cursor and Codex CLI.
One payment, lifetime access. 2 skills unlock instantly in your library.
What's included
2 skillsSub-millisecond columnar telemetry, recursive tool loop circuit breaker (LOOP_DETECTED), and token quota guard for autonomous AI agents in 100% pure Rust (#![forbid(unsafe_code)]). Includes pre-configured Enterprise Pro license key for unlimited session telemetry.
Pre-execution tool-call firewall, cloud credential scanner, and atomic blast-radius workspace rollback engine in pure Rust (#![forbid(unsafe_code)]). Blocks destructive shell/SQL/Git commands, detects leaked API keys and prompt injections, and byte-for-byte restores unauthorized file drift.
See it in action
Prasasti: Agent Sentinel & Columnar Telemetry Engine
Example session with this skill installed
Record telemetry for the 'cargo_test' step with 145ms latency and 2,500 tokens, then check if our active agent loop circuit breaker has been tripped within the last 5 minutes (max 5 repeats, 50,000 token ceiling).
- Read your context and instructions
- Compiled the prasasti
Telemetry & Circuit Breaker Assessment
The agent step invocation was committed to Prasasti's hardware-CRC32 Write-Ahead Log. The sliding-window circuit breaker evaluation completed in
18 microseconds with zero runtime allocations.
| Telemetry Dimension | Value | Threshold / Limit | Circuit Status |
|---|---|---|---|
| Ingestion Status | RECORDED | Hardware CRC32 Validated | Committed |
| Monitored Action | cargo_test | Active Agent Tool | Normal |
| Window Invocation Count | 3 repeats | 5 repeat maximum | ALLOW |
| Cumulative Tokens | 7,500 tokens | 50,000 ceiling | ALLOW |
| Mean Step Latency | 142.6 ms | Monitored SLA | Nominal |
| Circuit Breaker Action | ALLOW | Safe to Proceed | Clear |
{
"status": "ALLOW",
"reason": "OK",
"symbol": "cargo_test",
"repeat_count": 3,
"max_repeats": 5,
"total_tokens": 7500.0,
"max_tokens": 50000.0,
"mean_latency_ms": 142.6,
"scanned_segments": 1,
"skipped_segments": 0,
"license_tier": "ENTERPRISE_PRO_V1"
}
Next Steps
- Tool execution is authorized to proceed; no runaway recursive loop detected.
- Telemetry will remain persisted across sessions in the columnar segment store.
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 these skills and uses them on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every skill in this bundle goes through our trust checks.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.