---
title: "stdtel"
description: "Telemetry for standards-as-skills: attributes token cost and policy outcomes to individual skills across Claude Code and GitHub Copilot."
canonical: https://agentpluginsdirectory.com/plugins/stdtel
last-updated: 2026-09-13
---

# stdtel
Telemetry for standards-as-skills: attributes token cost and policy outcomes to individual skills across Claude Code and GitHub Copilot.
- Slug: stdtel
- Publisher: amiable-dev
- Repository: https://github.com/amiable-dev/skills-telemetry
- Manifest: plugin.json
- Version: 0.2.3
- License: MIT
- Category (editorial): other
- Skills: 3 (stdtel-onboard, stdtel-query, structured-logging)
- MCP servers: 0
- Stars: 0
- Repository created: 2026-09-10
- Repository last pushed: 2026-09-13
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/stdtel
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What stdtel does, in the publisher's words

Telemetry and metadata capture for standards-as-skills: attributes token cost and outcomes to individual skills across Claude Code and GitHub Copilot, joined to policy (OPA/Rego), delivery (Linear/GitHub) and quality data. Design rationale: docs/design-proposal.md.

Metadata only. No prompt, response or file content is ever emitted; the collector drops it again as defence in depth. If it runs on your machine, docs/for-developers.md lists every field that leaves it, and export STDTEL_DISABLED=1 turns it off entirely.

Telemetry starts producing plausible-looking ratios on day one. Most of them mean nothing yet. The phases below are set by data volume, not elapsed time, how long each takes depends entirely on team size, and a small team may never leave the first one.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/amiable-dev/skills-telemetry/HEAD/README.md

## Skills

- stdtel-onboard: Bring an existing SKILL.md up to the standards-telemetry contract so the skill can be measured, adds the metadata block, picks a standard_id and policy_ids, and validates. Use when onboarding a skill to telemetry, when stdtel-validate fails, or when a skill reports as unversioned in the data.
- stdtel-query: Query standards-telemetry data to answer questions about skill cost, token usage, cache-hit rate, and delivery outcomes, tokens per merged PR, tokens per cycle-time hour, first-time policy pass rate. Use when asked what a skill cost, which skills are expensive, how a harness compares, or to pull nu…
- structured-logging: Emit JSON structured logs with the platform's required fields and no PII, shipped via the standard Alloy/Fluent Bit pipeline.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.