proactive-telemetry

A set of rules that tells the coding agent to check live production data through TierZero, including logs, measurements, traces, deployments, and internal documentation.

In plain words
What is it for?
It is for investigating incidents, errors, alerts, traffic, timing, slow requests, recent deployments, and whether a code change affects a heavily used part of an application.
Why use it?
It helps answer questions using what is actually happening in a running system, instead of relying only on code or assumptions.

Cursor rule

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 rules/tierzeroai/tierzero-cursor/proactive-telemetry
Clone the repo
git clone --depth 1 https://github.com/TierZeroAI/tierzero-cursor
Per session 443 This file is loaded in full into every session.
When invoked 443 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin original 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 $0.00443 $0.00443
Opus 5 $0.00221 $0.00221
Sonnet 5 $0.00089 $0.00089
Haiku 4.5 $0.00044 $0.00044

Measured today against content hash 6be6843ea5d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

proactive-telemetry scanned grade A with 1 finding 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 today.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Call these directly by their bare names through the MCP interface — do not construct namespaced paths, do not shell out to `curl`, do not read Cursor's internal cache files (`SERVER_METADATA.json`, etc.) to discover them
plugins/tierzero/rules/proactive-telemetry.mdc · 33 lines

What it actually says

When to call TierZero

This workspace has the TierZero MCP server (tierzero) installed. It exposes tools that read live production telemetry across logs, metrics, traces, CI/CD, and knowledge bases.

Use it without being asked when:

  • The user is investigating an incident, alert, or production error.
  • The user is debugging behavior that depends on real traffic, real data, or real timing.
  • A code change touches a hot path and you don't know what calls it or how often.
  • A PR review hinges on whether something is actually broken in prod.
  • The user pastes a service name, error string, or stack trace from a real environment.

Available MCP tools

Call these directly by their bare names through the MCP interface — do not construct namespaced paths, do not shell out to curl, do not read Cursor's internal cache files (SERVER_METADATA.json, etc.) to discover them.

Tool Purpose
tierzero_ask Run an investigation. Pass a single query (plain English). Names a service, time window, and symptom. Returns grounded findings with evidence sources and any TierZero investigation URL to drill into.
tierzero_fetch_context Load a TierZero conversation, investigation, or artifact. Pass url (chat URL, investigation URL, or bare artifact UUID) and optional include_sources (default false; set true only when the user asks for source-by-source breakdowns).

When you call tierzero_ask, pass a specific query: name the service, give a time window, describe the symptom. Vague queries waste turns.

When NOT to call TierZero

  • Pure unit tests, doc-only edits, or local dev questions where production data is irrelevant.
  • Authentication: TierZero handles OAuth automatically through Cursor. If a tool call returns an auth error, tell the user to open Cursor Settings → MCP → tierzero and click Authorize, then retry. Do not try to set env vars or pass tokens manually.
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. today First seen · 33 lines · 443 tokens per session scan A 6be6843ea5d4

Subscribe to this mod's changes

proactive-telemetry is a cursor rule published in the GitHub repository TierZeroAI/tierzero-cursor (0 stars, last pushed 3mo ago), licensed MIT. It adds 443 tokens to every session, about $0.0022 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.