A local web dashboard for viewing a project's .planr/ work graph. It shows overviews, graphs, boards, lists, sprints, and activity without changing the project data.

Use it to open the project dashboard in a browser, choose a specific view, or serve a fixed snapshot without watching for file changes.

It gives you a live visual way to inspect project work instead of reading the underlying files. It runs separately in the background, so the command returns immediately.

dashboard — Command for Claude Code by openplanr/planr-pipeline

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.

Clone the repo

git clone --depth 1 https://github.com/openplanr/planr-pipeline

Made for: Claude Code.

Or install planr-pipeline, the plugin that ships this one along with the rest of its 8 skills, 10 commands, 1 hook.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/openplanr/planr-pipeline/dashboard/github.svg)](https://agentmods.dev/commands/openplanr/planr-pipeline/dashboard)

Your own site

<a href="https://agentmods.dev/commands/openplanr/planr-pipeline/dashboard"><img src="https://agentmods.dev/badge/commands/openplanr/planr-pipeline/dashboard/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/openplanr/planr-pipeline/dashboard"><img src="https://agentmods.dev/badge/commands/openplanr/planr-pipeline/dashboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 908 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00046	$0.00908
Opus 5.5	$0.00018	$0.00363
Sonnet 5.5	$0.00009	$0.00182
Haiku 4.5	$0.00005	$0.00091

Measured 1mo ago against content hash 577595ac30d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 1mo 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.

Origin

This is a copy

100% identical to dashboard — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

commands/dashboard.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/planr-pipeline:dashboard

Starts (or reuses) a persistent localhost HTTP server that serves the planr dashboard for the current project. The server is independent of the agent (hard rule 14): once DASHBOARD_URL: is printed the command STOPS — the server keeps running in the background and the agent does not block on it. The dashboard is read-only (no write-back to .planr/).

This command is additive and standalone. It NEVER runs the PO phase or the DEV phase, and it never auto-chains. It only resolves mode, negotiates a port, starts/reuses the server, prints the URL, and exits.

Flags

Flag	Meaning	Default
`--port N`	Bind to TCP port `N` on `127.0.0.1`.	env `DASHBOARD_PORT`, else `7473`
`--open`	After printing the URL, open it in the default browser.	off
`--no-watch`	Do not start the `.planr/` file watcher (serve a static snapshot).	watcher on
`--view graph\|board\|list`	Append `?view=<value>` to the printed URL so it opens on that view.	server default

Unknown flags are a fatal error (see procedures/fatal-error-format.md).

Port resolution

--port N > env DASHBOARD_PORT > default 7473. Resolution lives in procedures/dashboard-preflight.md.

Step sequence (mandatory order)

Preflight — run procedures/dashboard-preflight.md. It:
- validates the working directory (a .planr/ directory must exist),
- resolves mode via procedures/mode-detection.md (spec-driven vs default — both are first-class; the dashboard reads whichever is present),
- resolves the port (flag > DASHBOARD_PORT > 7473),
- performs reuse-if-running detection: if <planrHome>/dashboard-daemon/<port> names a live process AND GET http://127.0.0.1:<port>/health answers { ok: true }, reuse that server (do not start a second one),
- otherwise starts lib/dashboard/server.mjs (honouring --no-watch).
Start / reuse server — bind lib/dashboard/server.mjs on the resolved port (or confirm the reused one). The server registers GET /api/graph, GET /api/node/:id, GET /api/events (SSE), and static serving from lib/dashboard/app/.
Print the URL — emit exactly one line:
```
DASHBOARD_URL: http://localhost:<port>/
```
When --view is supplied, append ?view=<value> to that URL.
(optional) Open — if --open, open the printed URL in the default browser.
STOP. The command is complete the moment DASHBOARD_URL: is printed. Do not block, do not tail logs, do not run any further phase. The server keeps serving in the background until the operator stops it.

Read the full file on GitHub · 76 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.

1mo ago First seen · 76 lines · 46 tokens per session scan A 577595ac30d5

Subscribe to this mod's changes

dashboard is a command published in the GitHub repository openplanr/planr-pipeline (2 stars, last pushed 28d ago), licensed MIT. It adds 46 tokens to every session and 908 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to dashboard, differing in 2 lines, and is treated as a copy.

Claude Code Code Generation Project management ai-agents claude-code-plugin spec-driven subagents

iteration-drive

Drive or resume the selected locked iteration through Phase 2→6 — autonomous execute → iteration-close → PR → merge-ready loop → post-merge close. Takes no arguments.

btspoony/mstar-harness · 38 tokens

project-sprint

Sequential PDCA in the current session.

pactkit/claude-code-plugin · 7 tokens

octo-schedule

Manage scheduled workflow jobs for the Claude Octopus scheduler.

nyldn/claude-octopus · 24 tokens

octo-scheduler

Manage the Claude Octopus scheduled workflow runner daemon.

nyldn/claude-octopus · 15 tokens

Read the active sprint’s current status. Refresh stale compilation using grainulator compile --dir or grainulator.compile. Use the resulting nextactions with the user’s current scope and authorization. Output only the two Auto and Manual lists below, with no recap, status counters or offer to continue. Continue useful…

grainulation/grainulator · 0 tokens

amazing-e2e-check

Run explicitly requested E2E, browser, device, or installed-deployment scenarios in an independent verification workflow.

btspoony/mstar-harness · 29 tokens