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.
git clone --depth 1 https://github.com/robertsfeir/atelier-pipelineWrote 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.
[](https://agentmods.dev/rules/robertsfeir/atelier-pipeline/telemetry-metrics)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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_tokensunavailable: log0, append to content "token counts unavailable from Agent tool"cost_usdunavailable: setnull, log "Cost unavailable -- token counts not exposed by Agent tool"modelunavailable: set"unknown", skipcontext_utilizationandcost_usdcomputationcontext_utilizationunavailable: setnull(do not guess; requires both tokens and model)
Tier 2: Per-Unit Metrics
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.
- 9d ago First seen · 274 lines · 4,273 tokens per session scan A b4f1ece0f4c6
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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.