dashboard-sync

A command that publishes RACA experiment information to its live research dashboard. It gathers experiment metadata, activity logs, notes, and references to files stored on Hugging Face, a service for sharing machine-learning data and models.

In plain words
What is it for?
It updates the dashboard after artifact uploads, experiment-state changes, note changes, or completed result collection.
Why use it?
It keeps the dashboard in sync after experiments, notes, or result files change.

Command for Claude Code

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/zayne-sprague/dr-claude-code/dashboard-sync
Clone the repo
git clone --depth 1 https://github.com/Zayne-sprague/Dr-Claude-Code

Made for: Claude Code.

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 727 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00027 $0.00727
Opus 5 $0.00014 $0.00364
Sonnet 5 $0.00005 $0.00145
Haiku 4.5 $0.00003 $0.00073

Measured 2d ago against content hash 7a1a80dff341, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dashboard-sync scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X POST "${DASHBOARD_URL}/api/experiments/sync"
.claude/commands/raca/dashboard-sync.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dashboard Sync

Sync experiment metadata, activity logs, and artifact references to the live Research Dashboard.

When to run

  • After uploading any artifact to HuggingFace (so it appears in the Artifacts tab)
  • After writing or updating experiment notes or activity logs
  • After the harvest phase of an experiment pipeline
  • After any change to experiment state (phase transitions, go/no-go decisions)
  • When the user says "sync the dashboard", "update the website", or "refresh the dashboard"

Step 1: Check HUGGINGFACE_REPOS.md (if syncing a specific experiment)

If an experiment name was passed as an argument, read its artifact registry:

cat notes/experiments/<experiment_name>/HUGGINGFACE_REPOS.md 2>/dev/null

This confirms what HF datasets should appear in the Artifacts tab after sync.

Step 2: Run import_experiments.py

This reads all experiment data from notes/experiments/ — including configs, READMEs, activity logs, and HF repo lists — and uploads the aggregated data to the RESEARCH_DASHBOARD HF dataset.

cd tools/visualizer && .tools-venv/bin/python scripts/import_experiments.py

If the .tools-venv doesn't exist or the command fails:

# Fallback: use system python if venv is missing
cd tools/visualizer && python3 scripts/import_experiments.py

Capture the output. If it reports errors (missing files, HF auth failure), report them to the user.

Step 3: Trigger dashboard refresh

Tell the live HF Space to re-download the updated data:

# Dashboard URL is in .raca/config.yaml
DASHBOARD_URL=$(python3 -c "import yaml; print(yaml.safe_load(open('.raca/config.yaml'))['dashboard']['url'])" 2>/dev/null)

if [ -n "$DASHBOARD_URL" ]; then
    curl -s -X POST "${DASHBOARD_URL}/api/experiments/sync"
else
    echo "No dashboard URL configured — skipping remote refresh"
fi

Step 4: Report what was synced

Tell the user:

Dashboard synced:
  Experiments: N experiments updated
  Artifacts: list any new HF datasets found (from HUGGINGFACE_REPOS.md)
  URL: <dashboard_url> (if configured)

Read the full file on GitHub · 88 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. 2d ago First seen · 88 lines · 27 tokens per session scan A 7a1a80dff341

Subscribe to this mod's changes

dashboard-sync is a command published in the GitHub repository Zayne-sprague/Dr-Claude-Code (5 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 727 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.