logging

A command for configuring Docent session logging. Docent is a tool that can upload transcripts from sessions where its tools are used.

In plain words
What is it for?
Use it to check logging status, understand what is uploaded, change sharing settings, or remove uploaded Docent session data.
Why use it?
It shows the current logging state and lets you control whether eligible session transcripts are shared, including opting out or deleting uploaded data.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/transluceai/claude-code-plugins/logging
Clone the repo
git clone --depth 1 https://github.com/TransluceAI/claude-code-plugins
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 632 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00036 $0.00632
Opus 5 $0.00018 $0.00316
Sonnet 5 $0.00007 $0.00126
Haiku 4.5 $0.00004 $0.00063

Measured yesterday against content hash 0f6f33990ce8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

logging 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.

plugins/docent/commands/logging.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are helping the user configure Docent session logging. This controls uploading of Claude Code session transcripts, so be precise and faithful: relay the facts below exactly, apply only changes the user clearly asked for in this conversation, and never guess.

1. Show the current state

Run the status command and present its output:

uv tool run --quiet --from 'docent-python>=0.1.83' python -m docent.plugin.logging_config status

2. Make sure the user knows what session sharing means

Before changing anything, relay these facts (a faithful paraphrase is fine, but keep them exact):

  • Sessions in which a Docent MCP tool or skill was actually invoked are uploaded to Transluce's Docent prod servers to help improve Docent. The upload is the session's full raw transcript — prompts, file contents read by tools, command outputs.
  • Sessions that never touch Docent are not uploaded. Nothing is ever uploaded when the active profile targets a self-hosted or otherwise non-prod instance.
  • Session logging is inactive unless DOCENT_ENABLE_SESSION_LOGGING=1 is set. Within that enabled rollout, sharing is on by default and reversible right here at any time. Setting DOCENT_DISABLE_SESSION_LOGGING=1 is a hard kill switch on top of everything.
  • Already-uploaded data can be deleted at any time: a DELETE to {api_url}/claude-code/sessions with their API key removes the canonical capture and the analytics run managed by this pipeline. Offer to run this if they ask for deletion.

3. Ask what they want

Ask which they'd like: opt out, opt back in, or delete already-uploaded data. If the status output showed the active instance is not the analytics target, mention that nothing uploads from their current profile either way.

4. Apply their choice

Use exactly one CLI invocation per choice (all via uv tool run --quiet --from 'docent-python>=0.1.83' python -m docent.plugin.logging_config ...):

  • opt-out — stop uploading sessions
  • opt-in — resume uploading Docent-using sessions

Read the full file on GitHub · 44 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 · 44 lines · 36 tokens per session scan A 0f6f33990ce8

Subscribe to this mod's changes

logging is a command published in the GitHub repository TransluceAI/claude-code-plugins (6 stars, last pushed 5d ago), licensed Apache-2.0. It adds 36 tokens to every session and 632 once invoked, about $0.0002 per session on Opus 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 2026-08-31.