agentmods.dev

dancing-bear: Skill for Claude Code

.claude/skills/telemetry-analyze/SKILL.md

telemetry-analyze is a skill for Claude Code from dancing-bear-show/dancing-bear. It costs 40 tokens per session (2,052 once invoked), scanned A, original, MIT.

A guide for analyzing Claude Code session usage, including cost, efficiency, performance, and tool-call patterns. It reads session transcripts stored on the computer.

In plain words
What is it for?
Use it for session reviews, budget forecasting, anomaly detection, model comparisons where supported, and finding high-cost activity.
Why use it?
It helps identify expensive or inefficient sessions while clearly noting that the available data cannot provide a reliable cost split by model tier.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents; positional $N argument.

This is dancing-bear-show/dancing-bear's own configuration. It tells Claude Code how to work on dancing-bear itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dancing-bear configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./bin/telemetry history -d 7 # Sessions from last 7 days.

not rated 7repo yesterday A scan 40 tokens original MIT
View source ↗ dancing-bear-show/dancing-bear
Reuse

Borrowing it

Nothing to install: this file belongs to dancing-bear-show/dancing-bear. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dancing-bear-show/dancing-bear/main/.claude/skills/telemetry-analyze/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dancing-bear-show/dancing-bear

Made for: Claude Code.

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-analyze

README.md
[![agentmods](https://agentmods.dev/badge/skills/dancing-bear-show/dancing-bear/telemetry-analyze/github.svg)](https://agentmods.dev/skills/dancing-bear-show/dancing-bear/telemetry-analyze)
Your own site
<a href="https://agentmods.dev/skills/dancing-bear-show/dancing-bear/telemetry-analyze"><img src="https://agentmods.dev/badge/skills/dancing-bear-show/dancing-bear/telemetry-analyze/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-analyze

Your own site · 80×15
<a href="https://agentmods.dev/skills/dancing-bear-show/dancing-bear/telemetry-analyze"><img src="https://agentmods.dev/badge/skills/dancing-bear-show/dancing-bear/telemetry-analyze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,052 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00040 $0.02052
Opus 5.5 $0.00016 $0.00821
Sonnet 5.5 $0.00008 $0.00410
Haiku 4.5 $0.00004 $0.00205

Measured yesterday against content hash 2e89d78d59c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

telemetry-analyze 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 yesterday.

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.

.claude/skills/telemetry-analyze/SKILL.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Telemetry Analysis

Analyze Claude Code session cost, efficiency, and usage using ./bin/telemetry.

When to Use

  • Weekly/monthly cost reviews
  • Per-session and per-agent cost comparisons (see Model Attribution for what "model" can and cannot mean here)
  • Session performance analysis
  • Budget forecasting and anomaly detection
  • Identifying high-cost or high-tool-call sessions

Data Source

./bin/telemetry reads transcripts directly — no setup, no collector, always works. They live one directory per project under ~/.claude/projects, so the glob is ~/.claude/projects/*/*.jsonl (plus the older ~/.claude/projects/*/*/subagents/*.jsonl layout). A bare ~/.claude/projects/*.jsonl is one level too shallow and matches nothing.

Model Attribution — a limitation to report honestly

No transcript-backed command produces a per-model-tier cost split. Do not build an Opus/Sonnet/Haiku table from the commands in this skill — they carry no model-cost field, so such a table would be invented.

There is one path to a real model breakdown, and it is not one of these: ./bin/telemetry otel cost --breakdown model (also --perf, and --format json for a by_model object). It reads the local OTel store rather than transcripts, so it only has data when the collector has been running — with no collector it exits 0 and reports zeros, which is easy to mistake for "no cost this week". If a request genuinely needs per-tier costs, use that command and say the figures are OTel-sourced; if it returns zeros, see the otel-doctor skill rather than reporting $0.

What the transcript-backed commands below actually give you:

  • cost --group-by day — daily cost totals. The JSON rows carry day and est_cost only, no model field.
  • cost --group-by agent — per-agent calls and cost, again with no model field.
  • history — one model per session, taken from the session's first API event (src/telemetry/providers/transcript.py:128).
  • summary — one model per session, taken from the session's latest API event (_latest_model at src/telemetry/tui/_summary.py:40-44, which walks reversed(api_events)).

Read the full file on GitHub · 211 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. yesterday First seen · 211 lines · 40 tokens per session scan A 2e89d78d59c8

Subscribe to this mod's changes

telemetry-analyze is a skill published in the GitHub repository dancing-bear-show/dancing-bear (7 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 2,052 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.

Analytics and metricsautomationcalendarcligmailoauth2outlook
Related

telemetry-analyze compared with skills from other repositories

telemetry-analyze next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
telemetry-analyzedancing-bear-show/dancing-bearSkill7yesterdayMITA40Claude Code
gogolafkfreund/nixos_configSkill32yesterdayGPL-3.0A125Claude Code, Codex
google-workspace-authbobmatnyc/claude-mpmSkill1582mo agononeA22Claude Code
outlook-mcpmpalermiti/outlook-mcpSkill412d agoMITA96Claude Code, Codex
olkrlrghb/olkcliSkill2314d agoMITA28Claude Code, Codex
ghealthGoogle-Health-API/google-health-cliSkill2814mo agoApache-2.0A41Claude Code, Codex
ghealth-sharedGoogle-Health-API/google-health-cliSkill2814mo agoApache-2.0A22Claude Code, Codex