v-dashboard

A read-only browser dashboard for Compound V execution data, such as runs, larger work groups, job status, approval checks, and blockers. It can show either a saved HTML snapshot or a local live view.

In plain words
What is it for?
It is for monitoring runs and jobs, reviewing approval-check results, checking usage and timestamps, and tracking blockers.
Why use it?
It gives you a visual way to inspect existing execution state without changing, starting, stopping, or merging work.

Command

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/procoders/superpowers-v/v-dashboard
Clone the repo
git clone --depth 1 https://github.com/procoders/superpowers-v
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 747 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00080 $0.00747
Opus 5 $0.00040 $0.00374
Sonnet 5 $0.00016 $0.00149
Haiku 4.5 $0.00008 $0.00075

Measured 2d ago against content hash b80f4c2c5146, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

v-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 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.

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.

commands/v-dashboard.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are opening the Compound V observability dashboard. It is read-only and present-only: it renders the state that already exists under docs/superpowers/execution/** (runs, epics, jobs, scope-gate verdicts, usage, blocker ledger). It never dispatches, collects, merges, kills, or mutates anything — control stays in the CLI (/v:dispatch, /v:resume, /v:epic), which is the git-derived, human-gated moat. This is the same read-only data /v:status prints as text, rendered as a browser UI.

Args: {{args}}serve (live) or emit (static snapshot); default emit. Optional --port N (serve) / --out FILE (emit).

Deterministic mechanics live in scripts/compound-v-dashboard.py; it is pure stdlib, degrade-safe (renders what exists, honest "no runs/state yet"), and anti-ruflo — measured-only usage ( when unmeasured), real counts (never a fabricated %), real timestamps only.

Branch on {{args}}

  • serve (or --serve) → an ephemeral, read-only, 127.0.0.1-only live viewer that auto-refreshes as a run/epic progresses — the local equivalent of a competitor's live agent UI, minus the control surface:

    python3 scripts/compound-v-dashboard.py serve [--port 8787] [--execution-root docs/superpowers/execution]
    

    It binds 127.0.0.1 only (never 0.0.0.0), serves GET/HEAD only, is realpath-contained to the execution root, and runs in the foreground until you Ctrl-C — it never backgrounds, never auto-launches, and writes nothing to any run dir. Print the http://127.0.0.1:<port>/ URL for the user to open, and remind them it stops on Ctrl-C.

  • emit (default, or --html) → a self-contained static HTML snapshot (data inlined, offline, theme-aware — good for sharing / audit), written to docs/superpowers/execution/dashboard.html (git-ignored build artifact):

    python3 scripts/compound-v-dashboard.py emit [--out docs/superpowers/execution/dashboard.html] [--execution-root docs/superpowers/execution]
    

    Print the file://… path for the user to open.

Read the full file on GitHub · 41 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 · 41 lines · 80 tokens per session scan A b80f4c2c5146

Subscribe to this mod's changes

v-dashboard is a command published in the GitHub repository procoders/superpowers-v (35 stars, last pushed 2d ago), licensed MIT. It adds 80 tokens to every session and 747 once invoked, about $0.0004 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 2026-08-30.