agentmods.dev

disconnect

disconnect is a command for Claude Code from pydantic/skills. It costs 13 tokens per session (354 once invoked), scanned A, original, MIT.

A command for stopping native Claude Code session recording while leaving Logfire access and skills available.

In plain words
What is it for?
It is for previewing, confirming, and checking the removal of Claude's session-telemetry settings.
Why use it?
It prevents users from removing the wrong connection or project settings when they only want to stop session capture.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the logfire plugin — 10 skills, 7 commands, 1 MCP server shipped together

not rated 151repo +4 9d ago A scan 13 tokens original MIT

Good fit It is for previewing, confirming, and checking the removal of Claude's session-telemetry settings.

Compare 6 commands from other repositories ↓
View source ↗ pydantic/skills
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add pydantic/skills
Claude Code
/plugin install logfire

Made for: Claude Code.

Or install logfire, the plugin that ships this one along with the rest of its 10 skills, 7 commands, 1 MCP server.

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 disconnect

README.md
[![agentmods](https://agentmods.dev/badge/commands/pydantic/skills/disconnect/github.svg)](https://agentmods.dev/commands/pydantic/skills/disconnect)
Your own site
<a href="https://agentmods.dev/commands/pydantic/skills/disconnect"><img src="https://agentmods.dev/badge/commands/pydantic/skills/disconnect/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 disconnect

Your own site · 80×15
<a href="https://agentmods.dev/commands/pydantic/skills/disconnect"><img src="https://agentmods.dev/badge/commands/pydantic/skills/disconnect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 354 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 $0.00013 $0.00354
Opus 5.5 $0.00005 $0.00142
Sonnet 5.5 $0.00003 $0.00071
Haiku 4.5 $0.00001 $0.00035

Measured 21d ago against content hash 5a484862a422, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

disconnect 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 21d ago.

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.

plugins/logfire/commands/disconnect.md · 32 lines

What it actually says

Stop Logfire session capture

This command removes native Claude telemetry configuration, not the remote project, project token, account login, MCP connection, or application instrumentation. Explain that distinction and confirm the user's intent. If the user's request is ambiguous, ask whether they want to stop session capture, disconnect MCP, or both. If MCP-only, use Claude's native controls and skip the telemetry runtime entirely. Do not make users stop capture just to disconnect MCP, or clear their MCP login when they only asked to stop capture.

Run python3 "${CLAUDE_PLUGIN_ROOT}/scripts/agent_runtime.py" without --install. Using its returned executable and data directory:

  1. Preview --beta --no-input --output json agent claude --data-dir <data_dir> remove --dry-run.
  2. With confirmation, run the same operation with --yes instead of --dry-run.
  3. Recheck agent claude ... status. Report the actual result and ask the user to restart Claude to stop exports from already-running sessions.

Do not delete the managed runtime or credential directory while the saved header helper may still reference them. The CLI refuses removal if managed fields were edited; surface that conflict rather than deleting fields by hand. If runtime or credentials are missing, do not claim capture has stopped or install software without asking. Help locate the original configuration.

Disabling/uninstalling the plugin is not a substitute for this operation. If the user also wants to disconnect MCP, use Claude's native /mcp controls to clear that connection separately. Do not revoke remote tokens unless asked.

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. 21d ago First seen · 32 lines · 13 tokens per session scan A 5a484862a422

Subscribe to this mod's changes

disconnect is a command published in the GitHub repository pydantic/skills (151 stars, last pushed 9d ago), licensed MIT. It adds 13 tokens to every session and 354 once invoked, about $0.0001 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 2026-10-17.

CloudDevOps and cloud
Related

disconnect compared with commands from other repositories

disconnect next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
disconnectpydantic/skillsCommand1519d agoMITA13Claude Code
cost-optimizewshobson/agentsCommand42kyesterdayMITA26Claude Code
deploybutterbase-ai/butterbase-skillsCommand5356d agoMITA20Claude Code
envvercel/vercel-pluginCommand326yesterdaynoneA35Claude Code
firebase-publishPierry/harness-kitCommand41mo agoMITA20Claude Code
scanprajapatimehul/claude-aws-cost-saverCommand244mo agoMITA6Claude Code
migrationdatabayt/hogwartsCommand183d agononeA4Claude Code