logfire-codex-connection — Claude Code skill: what it does
logfire-codex-connection — a Claude Code skill that connects Codex to Logfire, checks connection status, and stops session recording. Runs when managing Codex telemetry and session logging.
MIT 235 installs ★ 156 updated 2026-10-16
npx skills add pydantic/skills --skill logfire-codex-connection -a claude-codeWhat logfire-codex-connection does
The skill connects Codex to Logfire, checks status, and manages session recording without triggering unauthorized setup checklists. It relies on bundled scripts like ../../scripts/agent_runtime.py --agent codex located in the installed skill directory. Status requests never grant permissions to modify or repair configurations.
Session recording and MCP access operate independently. Telemetry setup and exporter installation remain with the native Logfire CLI without altering existing application instrumentation or model provider routing.
The routine finishes by reporting MCP access, capture destination, and delivery evidence as distinct facts.
What it helps with
- connect Codex to Logfire
- check Logfire connection status
- stop Codex session recording in Logfire
Example prompts for the agent
- Connect Codex to Logfire
- Check logfire-codex-connection status
- Disconnect logfire-codex-connection session recording
How to install logfire-codex-connection
1Skills CLI (Vercel)
npx skills add pydantic/skills --skill logfire-codex-connection -a claude-code2Manually: put the files in place
~/.claude/skills/logfire-codex-connection/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/logfire-codex-connection/
1Skills CLI (Vercel)
npx skills add pydantic/skills --skill logfire-codex-connection -a codex2Manually: put the files in place
.agents/skills/logfire-codex-connection/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add pydantic/skills --skill logfire-codex-connection -a cursor2Manually: put the files in place
.cursor/skills/logfire-codex-connection/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install pydantic/skills plugins/logfire/skills/logfire-codex-connection2Manually: put the files in place
.github/skills/logfire-codex-connection/SKILL.md1Skills CLI (Vercel)
npx skills add pydantic/skills --skill logfire-codex-connection -a gemini-cli2Platform CLI
gemini skills install https://github.com/pydantic/skills --path plugins/logfire/skills/logfire-codex-connectionManually: put the files in place
.devin/skills/logfire-codex-connection/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add pydantic/skills --skill logfire-codex-connection -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about logfire-codex-connection
How to install logfire-codex-connection in Claude Code?
Run npx skills add pydantic/skills --skill logfire-codex-connection -a claude-code and use ~/.claude/skills/logfire-codex-connection/SKILL.md.
What does logfire-codex-connection do?
It links Codex to Logfire, checks operational status, and stops session capture without altering model gateway routing.
What is required to run logfire-codex-connection?
Node.js environment with npx to fetch the skill package and the native Logfire CLI for telemetry configuration.
Source text
SKILL.md · MIT
--- name: logfire-codex-connection description: Connect Codex itself to Logfire, check connection status, or stop session recording. Use for this plugin's MCP access and optional native Codex telemetry, not application instrumentation or AI Gateway routing. --- # Connect Codex to Logfire Help the user connect, check status, or disconnect without making them run a setup checklist. Honor the requested operation; a status request never grants permission to install, authenticate, or repair anything. For connection, ask only if missing: "Would you like to query Logfire, record your Codex sessions, or both?" MCP access and recording are independent. Do not require CLI login for working MCP, or MCP read access to record sessions. - **Connect:** follow [connection setup](references/connect.md). - **Status:** follow [status and removal](references/status.md#status). - **Disconnect:** follow [status and removal](references/status.md#disconnect). Resolve bundled scripts relative to this installed skill directory. The runtime helper is `../../scripts/agent_runtime.py --agent codex`; the explicit agent selects Codex's separate runtime and project credential directory. Quote paths as single arguments. Do not assume `CLAUDE_PLUGIN_ROOT` exists in Codex. Leave telemetry configuration and exporter installation to the native Logfire CLI. Do not add custom transcript hooks, copy credentials, open secret-bearing Codex/exporter configuration files, or start a nested coding session for setup. Keep existing application instrumentation, model providers, and Gateway routing unchanged. Plugin installation is not consent to session capture. Finish with MCP access, capture mode/destination, and delivery evidence as separate facts. Give one next action. "Configured" does not mean data arrived.
© pydantic · MIT · pydantic/skills