# Send Agent Telemetry

Stream coding-agent session telemetry (prompts, tool calls, model requests, tokens and...

- Repository: https://github.com/ParadevAI/Paradev (15823 stars)
- Category: AI and agents
- License: see repository
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add ParadevAI/Paradev --skill send-agent-telemetry -g -a claude-code -y`
Codex: `npx skills add ParadevAI/Paradev --skill send-agent-telemetry -g -a codex -y`
Cursor: `npx skills add ParadevAI/Paradev --skill send-agent-telemetry -g -a cursor -y`
Gemini CLI: `npx skills add ParadevAI/Paradev --skill send-agent-telemetry -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add ParadevAI/Paradev`

## Description

Stream coding-agent session telemetry (prompts, tool calls, model requests, tokens and cost) from Claude Code or Codex into Sazabi over OpenTelemetry, with privacy settings chosen on purpose. Use when the user wants observability for their coding agents or agent fleet, to track agent token usage or cost, to audit what agents ran, or to send agent telemetry to Sazabi.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# See what your agents did

Claude Code and Codex have built-in OpenTelemetry exporters. Pointed at Sazabi,
every session becomes searchable: prompts, tool calls and results, model
requests with token counts and cost. Then "what did the agents run last night"
and "which sessions cost the most" are questions for `sazabi/logs.ask`.

## 0. How the tools work

The Sazabi MCP server lists only two tools, `search` and `execute`. Browse
Sazabi's operations with `search` and `namespace: "sazabi"` (an empty query
without a namespace lists connected connectors, not Sazabi operations). Before
calling one, repeat `search` with `namespace: "sazabi"`, the hit's full name as
the query, and `includeInputSchema: true` to load its arguments. Then run it
with `execute` as `{ name, arguments }`, the name copied from the hit (for
example `sazabi/logs.ask`).

## 1. Decide what may leave the machine

Ask before exporting prompt text. Prompts and tool inputs can contain code,
customer data and credentials. Codex always exports tool-call arguments and
truncated results, whatever the prompt setting, so say that plainly when the
user picks Codex. Default to prompts off unless the user opts in.

## 2. Get an intake URL per agent

Run `sazabi/logSources.list`. If there is no source for this agent yet, create
one with `sazabi/logSources.create` in manual mode (one source per agent:
Claude Code, Codex) and use the intake endpoint it returns. Keep the URL out of
any committed file.

## 3. Configure the agent

**Claude Code** reads the `env` block of `~/.claude/settings.json` (or a
project's `.claude/settings.local.json`, which must stay untracked):

```json
{
  "env": {
    "CLAUDE_CODE_ENABLE_TELEMETRY": "1",
    "OTEL_LOGS_EXPORTER": "otlp",
    "OTEL_EXPORTER_OTLP_PROTOCOL": "http/protobuf",
    "OTEL_EXPORTER_OTLP_ENDPOINT": "<intake URL>",
    "OTEL_LOG_USER_PROMPTS": "0",
    "OTEL_LOG_ASSISTANT_RESPONSES": "0"
  }
}
```

The rest: https://github.com/ParadevAI/Paradev/blob/HEAD/plugins/sazabi/skills/send-agent-telemetry/SKILL.md