agentleFS
ewebdzineewebdzine/claude-code-time-tracker/skills/setup/SKILL.md

setup

Skill0 starsChanged 4 months agoMITView on GitHub

One-time local install for the Claude Code Time Tracker dashboard. Copies the app out of the plugin into a stable working directory (~/.claude-time-tracker), installs its dependencies with npm, and verifies it's ready - no API keys, no account, nothing leaves the machine. Run when the user types /time-tracker:setup, or says "install the time tracker", "set up claude code time tracker", "get the time tracker running", "install the dashboard". Re-running is safe and also acts as an update.

  • Deletes or force-pushes
  • Installs packages

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-voice-transcription, add-discord and 10 more.

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.
  • juancruzmunozalbeloSkill

    add-voice-transcription

    Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

    Also in 5 projects that use this

  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • juancruzmunozalbeloSkill

    add-telegram-swarm

    Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

    Also in 7 projects that use this

  • +8 more from microsoft

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Check Node: Run node --version. The app needs Node 20 or newer.

    line 21
  2. Very specific:

    If Node is missing or older, stop and tell the user to install it (nodejs.org, or nvm install 20).

    line 22
  3. Very specific:

    Pick the working directory: Default APP_DIR="$HOME/.claude-time-tracker".

    line 25
  4. Very specific:

    Run /time-tracker:launch to open the dashboard.

    line 57

“Common” is measured: kept by at least 6 in 10 of the 171 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

Setup - install the Time Tracker locally

Stand up the dashboard on this machine so /time-tracker:launch can open it. This is a 100% local tool: it reads the Claude Code transcripts already in ~/.claude, computes idle-aware active time, and serves a dashboard on localhost. No API key, no account, and no data ever leaves the machine. Scoring prompts (/time-tracker:score) and hosting it (/time-tracker:deploy-vercel) are separate, optional add-ons.

App source is the plugin's own directory (${CLAUDE_PLUGIN_ROOT} - the Next.js project that ships in this plugin). The running copy lives in ~/.claude-time-tracker so a plugin update never clobbers node_modules and vice-versa. This skill (re)syncs source → working copy, so running it again is how you update after upgrading the plugin.

How to run

  1. Check Node. Run node --version. The app needs Node 20 or newer.
    • If Node is missing or older, stop and tell the user to install it (nodejs.org, or nvm install 20). Do not try to install Node for them.
  2. Pick the working directory. Default APP_DIR="$HOME/.claude-time-tracker".
    • Honour an existing $CCTI_APP_DIR if the user set one; otherwise use the default.
  3. Sync the app from the plugin into the working dir, preserving an existing node_modules (so re-runs are fast). Prefer rsync; fall back to cp if it's absent:
    mkdir -p "$APP_DIR"
    if command -v rsync >/dev/null; then
      rsync -a --delete \
        --exclude node_modules --exclude .next --exclude .git \
        "$CLAUDE_PLUGIN_ROOT"/ "$APP_DIR"/
    else
      cp -R "$CLAUDE_PLUGIN_ROOT"/. "$APP_DIR"/
      rm -rf "$APP_DIR/.git" "$APP_DIR/.next"
    fi
  4. Install dependencies:
    cd "$APP_DIR" && npm install
    This can take a minute on first run. If it fails, show the user the actual npm error rather than guessing.
  5. Verify the build toolchain resolved:
    test -d "$APP_DIR/node_modules/next" && echo "OK: next installed"
  6. Report success and tell the user exactly what's next. Keep it short:
    • Installed to ~/.claude-time-tracker.
    • Reads your local ~/.claude logs - nothing is uploaded.
    • Run /time-tracker:launch to open the dashboard.
    • Optional: /time-tracker:deploy-vercel to put it online behind a private login.

Notes

  • Where are the logs? The app reads ~/.claude/projects/**/**.jsonl by default. If the user keeps them elsewhere, they can set CLAUDE_DIR when launching (the launch skill covers this).
  • Nothing to configure for local use. Auth, email, and cloud storage are all off unless the corresponding env vars are set - which only happens via /time-tracker:deploy-vercel.
  • Idempotent. Safe to re-run anytime; it re-syncs the latest app code and reinstalls.

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.