agentleFS
egregore-labsegregore-labs/egregore/.claude/skills/telemetry/SKILL.md

telemetry

Skill293 starsChanged 10 days agoMITView on GitHub

Manage local-first telemetry — status, inspect, export, opt in/out, clear, or explicitly share a disclosed dataset. Use for /telemetry, 'turn off telemetry', or 'what data do you collect'.

  • Reads credentials

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Not this: viewing telemetry across all registered orgs (internal, admin only) → /telemetry-admin

    line 11
  2. Very specific:

    Use {count} for the number after inspect or show in the command's arguments, or 10 when omitted, escaping embedded single quotes as '\'':

    line 54
  3. Distinctive:

    Only after the user freshly confirms this exact proposal, run the printed command containing its one-time token.

    line 84

“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Manage telemetry settings. Shows status by default.

When to invoke

User says: "/telemetry", "telemetry status", "turn off telemetry", "disable telemetry", "what data do you collect", "inspect/export/share my telemetry events", "clear telemetry buffer" Not this: viewing telemetry across all registered orgs (internal, admin only) → /telemetry-admin

Arguments

  • status (default) — show whether telemetry is enabled, buffer size, opt-out method
  • off or disable — disable telemetry (sets telemetry: false in state file)
  • on or enable — re-enable telemetry
  • inspect [N] or legacy show [N] — show last N buffered events (default 10)
  • export <path> — validate and copy the local JSONL dataset; never uploads
  • share — disclose the exact local dataset and prepare a short-lived confirmation token
  • share --confirm <token> — send only the unchanged, previously disclosed dataset to the same target
  • clear — delete local telemetry buffer

What to do

Parse the argument (default to status if none given).

status (default)

bash bin/telemetry.sh status

Show the output to the user.

off / disable

bash bin/telemetry.sh disable

Confirm: "Telemetry disabled. No events will be collected until you run /telemetry on."

on / enable

bash bin/telemetry.sh enable

Confirm: "Telemetry re-enabled."

inspect [N]

Use {count} for the number after inspect or show in the command's arguments, or 10 when omitted, escaping embedded single quotes as '\'':

bash bin/telemetry.sh inspect '{count}'

Show the output. If empty, say "No buffered events."

export <path>

bash bin/telemetry.sh export "<path>"

Report the resulting local path. Export validates the same content-free event envelope used by sharing. It does not grant permission to upload the file.

share

First prepare the proposal. This performs no network I/O:

bash bin/telemetry.sh share

Show the complete output: target, event count, bytes, dataset hash, field list, exclusions, expiry, and exact confirmation command. Then stop. Do not infer confirmation from the request to share, a prior share, notification consent, or any unattended workflow.

Only after the user freshly confirms this exact proposal, run the printed command containing its one-time token. A changed target, changed buffer, expired token, or bad token requires a new proposal. Local events remain after a successful share.

Local instances have no default outbound sink. They may export or name an explicit endpoint. The former public relay is retired: --legacy-public-relay now refuses and sends nothing.

clear

bash bin/telemetry.sh clear

Confirm: "Local telemetry buffer cleared."

What is collected

Structured identifiers and metrics: event/task/actor/org/session identifiers, timestamps, retrieval type, privacy-safe lexical/vector fingerprints when configured, returned/opened artifact identifiers, ranks/order, tool-call count, latency, token counts, writeback outcome, success/failure, and index-spec version. Metric strings are bounded identifiers/enums, not prose.

What is NEVER collected

Raw prompts/queries, passages, file paths, file contents, code, env var values, secrets, conversation content, prose error messages, or command arguments that might contain user content.

Opt-out methods

  1. /telemetry off — persistent opt-out via state file
  2. EGREGORE_NO_TELEMETRY=1 in .env — env var opt-out
  3. DO_NOT_TRACK=1 — standard env var opt-out

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.