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 skills add BlackBeltTechnology/pi-agent-dashboard --skill pi-dashboard-watchgit clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboardWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/pi-dashboard-watch)<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/pi-dashboard-watch"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/pi-dashboard-watch/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/pi-dashboard-watch"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/pi-dashboard-watch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00066 | $0.00956 |
| Opus 5.5 | $0.00026 | $0.00382 |
| Sonnet 5.5 | $0.00013 | $0.00191 |
| Haiku 4.5 | $0.00007 | $0.00096 |
Grade B, and why
pi-dashboard-watch scanned grade B with 2 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 today.
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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
`curl -s -X POST BASE/api/questions/QUESTION_ID/answer -H 'Content-Type: application/json' -d '{"answer":"…"}'`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -s BASE/api/questions/QUESTION_ID`. Ask the user unless they told you how to answer this kind of How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watch pi sessions for events
The dashboard streams agent events at GET BASE/api/events/stream (Server-Sent Events).
scripts/watch-events.sh follows that stream and prints one line per event:
PI-EVENT ready
PI-EVENT status {"type":"status","sessionId":"…","from":"streaming","to":"idle"}
PI-EVENT question_opened {"type":"question_opened","sessionId":"…","questionId":"…","questionType":"select","preview":"Push to main?","sessionLabel":"…"}
PI-EVENT question_closed {"type":"question_closed","sessionId":"…","questionId":"…","reason":"answered"}
PI-EVENT session_added {"type":"session_added","sessionId":"…","status":"active","cwd":"/path","name":"…"}
PI-EVENT session_removed {"type":"session_removed","sessionId":"…"}
PI-EVENT error <reason>
Run pi-dashboard-bootstrap first and use its literal BASE.
Start the watcher
Start it with the Monitor tool, so every line reaches you as a notification, also while you are idle.
Set timeout_ms to the maximum. A monitor expires after at most 30 minutes, so start it again when the
expiry notice arrives and you still control those sessions. Watch only what you need: narrow with --session (full ids from GET BASE/api/sessions, comma-separated)
and --types. One watcher per controlling session is enough. Restart it with a new filter rather than
starting a second one.
sh "${CLAUDE_SKILL_DIR}/scripts/watch-events.sh" BASE --session ID --types status,question_opened,question_closed
Types: session_added, status, session_removed, question_opened, question_closed. With no --types
you get all of them. Status values are active, idle, streaming and ended.
If Monitor is not available, run the same command as a background Bash call with --once added. It exits
after the first event, which wakes you. Read the line, act, and start it again if you still need to watch.
When the dashboard needs a token (the watcher prints PI-EVENT error http …), follow "When a call is refused"
in the pi-dashboard-control skill. Pass the header file with --header-file, chained after the check,
so the token only reaches a verified dashboard:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today First seen · 68 lines · 66 tokens per session scan B 726fdcab44fa
pi-dashboard-watch is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (331 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 956 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-26.
Other skills, from other repositories
ask-user
Ask the human structured questions via nui HITL instead of plain chat text.
starfleet-sessions
Ship session and workspace management — spawning ships, session attach/stop, git worktrees, web console, deployment. Load when launching/administering ships or managing the fleet web console.
starfleet-timer
Set timers instead of blocking a session with sleep/watch-loops (e.g. waiting for a GitHub Actions run): the timer fires a comms directive into the fleet at the scheduled time, and the poller injects it into the owning ship's next turn — no background process, no blocking, survives a session restart.
kungfu-agent-onboarding
Use when a user asks to understand, start, inspect, extend, or safely operate installed Kungfu; verify the installed pack, select one intent route, personalize the explanation, and propose one smallest safe next action.
goga-cookbook
Principles for applying DSL specification in cell and CODEMANIFEST design.
goga-plan-by-design
Compile a design document into a ralphex execution plan.