telemetry-metrics

telemetry-metrics is a cursor rule for Cursor from robertsfeir/atelier-pipeline. It costs 4,273 tokens per session, scanned A, original, Apache-2.0.

A reference file defining telemetry fields, cost estimates, and alert thresholds for an agent pipeline. Telemetry is the recorded data about each tool run, such as duration and token use.

In plain words
What is it for?
Use it when capturing per-invocation metrics, estimating costs, checking pipeline alerts, or interpreting missing telemetry values.
Why use it?
It gives the pipeline a consistent way to record performance, retries, model details, and unavailable measurements.

Cursor rule for Cursor

Written for Cursor: a Cursor plugin manifest. Also seen: positional $N argument.

Good fit Use it when capturing per-invocation metrics, estimating costs, checking pipeline alerts, or interpreting missing telemetry values.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/robertsfeir/atelier-pipeline/telemetry-metrics
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.

Clone the repo
git clone --depth 1 https://github.com/robertsfeir/atelier-pipeline

Made for: Cursor.

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-metrics

README.md
[![agentmods](https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/telemetry-metrics/github.svg)](https://agentmods.dev/rules/robertsfeir/atelier-pipeline/telemetry-metrics)
Your own site
<a href="https://agentmods.dev/rules/robertsfeir/atelier-pipeline/telemetry-metrics"><img src="https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/telemetry-metrics/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for telemetry-metrics

Your own site · 80×15
<a href="https://agentmods.dev/rules/robertsfeir/atelier-pipeline/telemetry-metrics"><img src="https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/telemetry-metrics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,273 This file is loaded in full into every session.
When invoked 4,273 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.04273 $0.04273
Opus 5 $0.02136 $0.02136
Sonnet 5 $0.00855 $0.00855
Haiku 4.5 $0.00427 $0.00427

Measured 9d ago against content hash b4f1ece0f4c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

telemetry-metrics 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 9d 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.

.cursor-plugin/rules/telemetry-metrics.mdc · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Telemetry Metrics Reference

Eva reads this file at pipeline start alongside pipeline-operations.md to load metric schemas, cost estimation tables, and alert thresholds for telemetry capture.


Tier 1: Per-Invocation Metrics

Captured after every Agent tool completion by Eva.

Field Type Source Default When Unavailable
agent_name string Agent tool call context Required -- always known
pipeline_phase string Eva pipeline state Required -- always known
work_unit_id string ADR step ID (e.g., "ADR-0014-Step-1") Required -- always known
is_retry boolean Rework cycle count > 0 for this unit false
duration_ms integer Wall-clock end_time - start_time Always computable
model string Agent tool result metadata "unknown"
input_tokens integer Agent tool result metadata 0 (log "unavailable")
output_tokens integer Agent tool result metadata 0 (log "unavailable")
cache_read_tokens integer Agent tool result metadata 0
finish_reason string Agent tool result metadata "unknown"
tool_count integer Agent tool result metadata 0
turn_count integer Agent tool result metadata 0
context_utilization float (input_tokens + output_tokens) / context_window_max null when tokens unavailable
cost_usd float or null Computed from cost estimation table null when model unknown or pricing unavailable

Missing Data Handling (Tier 1)

  • input_tokens / output_tokens unavailable: log 0, append to content "token counts unavailable from Agent tool"
  • cost_usd unavailable: set null, log "Cost unavailable -- token counts not exposed by Agent tool"
  • model unavailable: set "unknown", skip context_utilization and cost_usd computation
  • context_utilization unavailable: set null (do not guess; requires both tokens and model)

Tier 2: Per-Unit Metrics

Read the full file on GitHub · 274 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. 9d ago First seen · 274 lines · 4,273 tokens per session scan A b4f1ece0f4c6

Subscribe to this mod's changes

telemetry-metrics is a cursor rule published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 4,273 tokens to every session, about $0.0214 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 2026-08-30.