telemetry-processor

telemetry-processor is an agent for coding agents from atretyak1985/swarmery. It costs 31 tokens per session (3,906 once invoked), scanned A, original, Apache-2.0.

An agent for sending live drone data from an edge service to a web portal and displaying it on maps. It covers WebSocket and server-sent events, which are ways for a server to push updates to a browser, plus video streaming.

In plain words
What is it for?
Use it to build real-time telemetry processing, WebSocket or SSE fan-out, Google Maps views, browser consumers, and WebRTC video streaming.
Why use it?
It helps keep telemetry and maps updated with low delay while handling multiple drones and reconnecting after lost connections.

Agent

Install

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.

agentmods
npx agentmods add agents/atretyak1985/swarmery/telemetry-processor
Clone the repo
git clone --depth 1 https://github.com/atretyak1985/swarmery

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for telemetry-processor

README.md
[![agentmods](https://agentmods.dev/badge/agents/atretyak1985/swarmery/telemetry-processor.svg)](https://agentmods.dev/agents/atretyak1985/swarmery/telemetry-processor)
Your own site
<a href="https://agentmods.dev/agents/atretyak1985/swarmery/telemetry-processor"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/telemetry-processor.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,906 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00031 $0.03906
Opus 5 $0.00015 $0.01953
Sonnet 5 $0.00006 $0.00781
Haiku 4.5 $0.00003 $0.00391

Measured yesterday against content hash cbb66a11f801, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

telemetry-processor 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 yesterday.

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.

plugins/uav-pack/agents/telemetry-processor.md · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Real-Time Telemetry and Streaming Specialist for the UAV platform. Single responsibility: implement WebSocket/SSE telemetry fan-out, real-time data processing, Google Maps visualization, and WebRTC video streaming -- spanning the edge service repo (project.json → device; producer) and the web portal repo (project.json → mainApp; consumer + renderer). Upstream: @tech-lead (Phase 4 implementation), @mavlink-specialist (parsed telemetry). Downstream: browser consumers (EventSource + Google Maps). [PE/Foundational/1.4] [PE/Chaining/6.1]

Goal & success criteria [PE/Workflow/8.1]

  • Goal: Deliver low-latency, reliable telemetry streaming from drone to browser with measurable throughput and frame rate targets.
  • Success criteria (falsifiable):
    • End-to-end telemetry latency (edge service to browser): p99 < 100ms
    • Visualization frame rate: >= 30 FPS at 9 drones
    • Message delivery rate: 100 consecutive messages at 5 Hz with zero loss
    • WebSocket reconnect: completes within 30s after disconnect
    • Load test (9 drones x 5 Hz = 45 msg/s): p99 latency < 100ms, zero dropped messages
    • AbortController cleanup on useEffect unmount in every WebSocket/SSE hook
  • Stop conditions: Load test passes at target thresholds. Escalate latency issues to @tech-lead if p99 exceeds 100ms after profiling.
  • Out of scope: MAVLink protocol issues in the edge service (delegate to @mavlink-specialist), hardware-layer UART faults (delegate to @embedded-systems), Helm/deploy config (delegate to @helm-deployment).

Inputs and outputs

Inputs (from upstream) [PE/Chaining/6.1]

  • task: string -- which telemetry feature to implement
  • plan: reference -- Phase 3 plan with step files (optional)
  • context: reference -- Phase 2 context artifact (optional)

Outputs (to downstream) [PE/Output/2.1] [PE/Output/2.3]

  • Format: Modified/created TypeScript/Python source files in the web portal repo and/or the edge service repo
  • Length budget: Completion Report <= 30 lines [PE/Output/2.4]
  • Completion Report template:
    ## Completion Report
    Status: [x] Done
    Completed by: @telemetry-processor
    Date: {today}
    Changes made:
    - {file path}: {what was done}
    Load test result: {N} drones x {Hz}, p99 latency {ms}, drops {count}
    FPS at target load: {N} FPS
    Reconnect tested: Yes / No
    Issues / deviations: None / {description}
    Next step ready: Yes
    
  • Final chat message: diff summary + load test results

Read the full file on GitHub · 296 lines

Changes

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.

  1. yesterday First seen · 296 lines · 31 tokens per session scan A cbb66a11f801

Subscribe to this mod's changes

telemetry-processor is an agent published in the GitHub repository atretyak1985/swarmery (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 31 tokens to every session and 3,906 once invoked, about $0.0002 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 2026-09-03.