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.
npx agentmods add commands/pathakcodes/learnfromclaude/dashboardgit clone --depth 1 https://github.com/pathakcodes/learnFromClaudeWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00009 | $0.00189 |
| Opus 5 | $0.00005 | $0.00095 |
| Sonnet 5 | $0.00002 | $0.00038 |
| Haiku 4.5 | $0.00001 | $0.00019 |
Grade A, and why
dashboard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Start the learnFromClaude dashboard server and open it in the default browser.
Run this command in the background (use Bash with run_in_background: true):
python3 "${CLAUDE_PLUGIN_ROOT}/server.py"
The server prints the URL (default: http://127.0.0.1:8765/) and auto-opens the browser. If port 8765 is taken, set LEARN_FROM_CLAUDE_PORT to a free port, e.g.:
LEARN_FROM_CLAUDE_PORT=8890 python3 "${CLAUDE_PLUGIN_ROOT}/server.py"
After launching, tell the user the dashboard is up and remind them of the keyboard shortcuts: / search · ←/→ nav · L like · S shuffle · , settings.
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.
- yesterday First seen · 20 lines · 9 tokens per session scan A 56452483b4b0
dashboard is a command published in the GitHub repository pathakcodes/learnFromClaude (2 stars, last pushed 4mo ago), licensed MIT. It adds 9 tokens to every session and 189 once invoked, about $0.0000 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.
Other commands, from other repositories
better-auth:add-plugin
Add a better-auth plugin to an existing project. Configures server and client plugins with proper imports.
bun:migrate
Migrate existing Node.js/npm projects to Bun.
pr-visual-diff
Post before/after stills + GIFs on a visual PR, captured headlessly with Playwright + ffmpeg.
open
Build the current project's claude-telemetry dashboard, then open it in the browser.
usage-report
Generate a self-contained HTML usage report for the current project (all time).
e2e
使用 Playwright 对 Web UI 进行端到端测试（支持视频录制、Trace 录制、控制台/网络日志捕获）.