Agent skill
token-dashboard
Open the Token Optimizer dashboard. Collects latest session data, regenerates the dashboard, and opens it in your browser.
Install this agent skill to your Project
npx add-skill https://github.com/alexgreensh/token-optimizer/tree/main/skills/token-dashboard
SKILL.md
Token Optimizer Dashboard
Opens an up-to-date dashboard showing your context usage trends, quality scores, session history, and skill management.
Instructions
- Resolve measure.py path:
MEASURE_PY=""
for f in "$HOME/.claude/skills/token-optimizer/scripts/measure.py" \
"$HOME/.claude/plugins/cache"/*/token-optimizer/*/skills/token-optimizer/scripts/measure.py; do
[ -f "$f" ] && MEASURE_PY="$f" && break
done
[ -z "$MEASURE_PY" ] && { echo "[Error] measure.py not found. Is Token Optimizer installed?"; exit 1; }
- Collect and open:
python3 "$MEASURE_PY" collect --quiet && python3 "$MEASURE_PY" dashboard
This collects the latest session data into the trends database, regenerates the dashboard HTML, and opens it in your default browser.
- Tell the user the dashboard is open and mention direct access:
- File:
~/.claude/_backups/token-optimizer/dashboard.html - Check if the persistent daemon is running:
nc -z 127.0.0.1 24842 2>/dev/null - If running, also mention: "Bookmarkable URL: http://localhost:24842/token-optimizer"
- If NOT running, do NOT mention the URL (it would give a connection error). Instead suggest: "Want a bookmarkable URL? Run:
python3 $MEASURE_PY setup-daemon"
- File:
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
token-optimizer
Audit your OpenClaw setup for token waste, context bloat, and cost optimization opportunities
fleet-auditor
Audit token waste across agent systems (Claude Code, OpenClaw, Hermes, OpenCode). Detect idle burns, model misrouting, and config bloat with dollar savings.
token-optimizer
Find the ghost tokens. Audit Claude Code setup, see where 25-38% of your context goes, fix it. Use when context feels tight.
token-coach
Context window coach. Proactive guidance for token-efficient Claude Code projects, multi-agent systems, and skill architecture.
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
Didn't find tool you were looking for?