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/rbinar/cli-dispatch/dashboardgit clone --depth 1 https://github.com/rbinar/cli-dispatchWhat 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 | $0.00021 | $0.00655 |
| Opus 5 | $0.00010 | $0.00328 |
| Sonnet 5 | $0.00004 | $0.00131 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
dashboard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
cli-dispatch dashboard
Launch the local web dashboard. It shows active Claude Code CLI sessions (across all projects, active pinned on top); click a session to see its flow, the subagents it spawned, and click a subagent to drill into its flow — plus a panel for the cli-dispatch worker delegations (DeepSeek / Antigravity / Codex / OpenCode / Copilot).
Read-only by default. Binds
127.0.0.1only. No config/secret access. An opt-in human-takeover capability, if explicitly installed, exposes a narrowly-scoped, authenticated write path to already-owned worker sessions only (no general shell, no arbitrary command) — currently supported for all five backends (DeepSeek / Antigravity / Codex / OpenCode / Copilot). This is the only long-running process the plugin starts — it serves until you stop it (the printedkill <pid>, or Ctrl-C if you runcli-dispatch-dashboardyourself in a terminal).
if ! command -v cli-dispatch-dashboard >/dev/null 2>&1; then
echo "cli-dispatch-dashboard not installed. Run /cli-dispatch:setup, then retry."
echo "(or run it from the repo: node plugins/cli-dispatch/scripts/dashboard-server.mjs)"
exit 0
fi
LOG="${TMPDIR:-/tmp}/cli-dispatch-dashboard.log"
nohup cli-dispatch-dashboard --no-open >"$LOG" 2>&1 &
PID=$!
# wait briefly for the bound URL to appear in the log
for i in 1 2 3 4 5 6 7 8; do
URL=$(grep -oE 'http://127\.0\.0\.1:[0-9]+' "$LOG" 2>/dev/null | head -1)
[ -n "$URL" ] && break
sleep 0.4
done
if [ -z "$URL" ]; then echo "Dashboard failed to start. Log: $LOG"; cat "$LOG" 2>/dev/null | tail -5; exit 0; fi
# open the browser (best-effort, cross-platform)
if command -v open >/dev/null 2>&1; then open "$URL" >/dev/null 2>&1 || true
elif command -v xdg-open >/dev/null 2>&1; then xdg-open "$URL" >/dev/null 2>&1 || true
elif command -v explorer.exe >/dev/null 2>&1; then explorer.exe "$URL" >/dev/null 2>&1 || true
fi
echo "Dashboard running → $URL (pid $PID)"
echo "Stop it with: kill $PID"
Tell the user the URL and that it's now open in their browser; remind them how to stop it.
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 · 47 lines · 21 tokens per session scan A 943c4740ee25
dashboard is a command published in the GitHub repository rbinar/cli-dispatch (5 stars, last pushed 13d ago), licensed MIT. It adds 21 tokens to every session and 655 once invoked, about $0.0001 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
rebase
Rebase current branch onto trunk (origin/master or origin/main), predict and resolve conflicts.
execute
Enter EXECUTE mode to implement approved plan.
innovate
Enter INNOVATE mode for brainstorming approaches.
research
Enter RESEARCH mode for information gathering.
verify
Adversarial spec-vs-implementation verification for a completed task. Dispatches the spec-mentor subagent with fresh context (no anchoring bias), parses its verdict (PASS / DRIFT / NEEDS-MARTY), and updates the verification queue. The v7.4.0 architectural replacement for a dedicated "mentor session.".
criar-skill
Use when creating new skills, automations, or specialized knowledge packages. Keywords: criar skill, nova skill, automatizar, conhecimento, TDD skill.