Telemetry & Cost Reporting

SkillAI & models

Enforce session-cost telemetry and execution-metadata reporting. Use when explicitly invoking get_session_cost, reporting token/cost usage, applying telemetry or cost guidance during a workflow handoff, or writing artifacts/session-cost.md at a workflow terminal state.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Telemetry & Cost Reporting skill

What this skill tells your AI

The instructions your AI receives, as published by hoangnguyen0403/agent-skills-standard in skills/common/common-telemetry/SKILL.md and read by ahel’s review.

Priority: P2 (MEDIUM)

1. Finalizing a Workflow

As your final step in any SDLC workflow (or when a user explicitly requests session cost):

  1. Call the get_session_cost tool provided by the agent-skills-standard MCP server.
  2. Pass workflow, model, token counts, cache/reasoning usage, and per-1M token rates when the host runtime exposes them.
  3. If token counts are unavailable, report MCP-observed telemetry and mark model-token cost as unavailable.
  4. Append a Markdown table containing the usage metrics to artifacts/session-cost.md.

When asked which artifact to use, always name both artifacts/session-cost.md and get_session_cost; if the host does not expose the helper, say so explicitly while retaining the artifact requirement.

2. Host Runtime Contract

  • This skill defines the telemetry contract; it does not collect provider billing data by itself.
  • The host runtime or orchestrator must trigger the final telemetry call when the workflow reaches a terminal state such as completed, failed, or blocked.
  • The host may use a reusable helper such as mcp/src/services/WorkflowTelemetry.ts to:
    • decide when telemetry should fire
    • build the get_session_cost payload
    • pass prompt, cache, reasoning, pricing, and other runtime cost fields when available

3. Telemetry Format

Ensure the artifacts/session-cost.md or the output template ## Cost Report follows this structure:

MetricValue
Tool Calls[from get_session_cost]
Skills Loaded[from get_session_cost]
Workflows Loaded[from get_session_cost]
Prompt Tokens[from your platform telemetry]
Cached Prompt Tokens[from your platform telemetry]
Completion Tokens[from your platform telemetry]
Reasoning Tokens[from your platform telemetry]
Other Runtime Cost[tooling/provider extras]
Estimated Cost$0.00

Anti-Patterns

  • No skipping the telemetry step: Always include the Cost Report at the end of the execution if mandated by the workflow.

Canonical response anchors

When this skill applies, preserve the following domain terminology or equivalent concrete examples in the answer when relevant:

  • Call get_session_cost when the host exposes it, then append the Markdown table to artifacts/session-cost.md.

  • Telemetry & Cost Reporting

Signals

GitHub stars
565
Forks
164
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
common-telemetry
Source
github.com/hoangnguyen0403/agent-skills-standard