swe-dashboard

swe-dashboard is a command for Claude Code from agentic-swe/agentic-swe. It costs 23 tokens per session (1,170 once invoked), scanned A, original, MIT.

A local browser dashboard that shows work items stored in a repository's .worklogs directory, including state, duration, token use, estimated cost, and activity summaries.

In plain words
What is it for?
Use it to monitor active or completed work, search records, refresh results, export data, and open work directories in VS Code.
Why use it?
It gives you one place to inspect and filter work progress and resource use across the repository.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the agentic-swe plugin — 22 commands, 3 agents, 3 hooks shipped together

Good fit Use it to monitor active or completed work, search records, refresh results, export data, and open work directories in VS Code.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add agentic-swe/agentic-swe
Claude Code
/plugin install agentic-swe

Made for: Claude Code.

Or install agentic-swe, the plugin that ships this one along with the rest of its 22 commands, 3 agents, 3 hooks.

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.

agentmods badge for swe-dashboard

README.md
[![agentmods](https://agentmods.dev/badge/commands/agentic-swe/agentic-swe/swe-dashboard.svg)](https://agentmods.dev/commands/agentic-swe/agentic-swe/swe-dashboard)
Your own site
<a href="https://agentmods.dev/commands/agentic-swe/agentic-swe/swe-dashboard"><img src="https://agentmods.dev/badge/commands/agentic-swe/agentic-swe/swe-dashboard.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,170 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 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 5.1 $0.00023 $0.01170
Opus 5 $0.00012 $0.00585
Sonnet 5 $0.00005 $0.00234
Haiku 4.5 $0.00002 $0.00117

Measured 7d ago against content hash 5d3b744a021e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

swe-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 7d 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/swe-dashboard.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/swe-dashboard

Read-only local dashboard for every work item under the target repo’s .worklogs/<id>/: state, track, task, duration, iteration usage, estimated cost (budget.cost_used / cap), token totals (budget.usage_totals when cost sync has run), counters (subagent spawns, panel runs), and rollup summaries (full repo, even when the table is paginated). The UI includes filters (all / active / completed), search, Refresh and optional auto-refresh (30s), Load more (paged GET /api/work-items?limit=&offset=, cap 200), a Δ cost column (increase since the previous refresh), Export JSON/CSV for the current view (export JSON includes api, projectRoot, exported_at, rollup), copy work dir path and VS Code open links per row, a by-state bar summary for the whole repo, and a compact transition timeline from history. The page uses the same visual language as the project site (Syne / IBM Plex Sans / JetBrains Mono, cyan–violet accents, grid backdrop, cards, and table chrome from site/src/index.css).

Demo data: from a checkout or target repo, run npm run seed-dashboard-demo (writes .worklogs/_demo-active and .worklogs/_demo-done; use --force to overwrite). Then open the dashboard for that repo.

Prompt

You are handling /swe-dashboard for: $ARGUMENTS

Resolve project root

  1. Default: the git / project root for the session (the directory that contains .worklogs/). If the user passed a path or work id, use it only when it clearly points at a repo root or a .worklogs/<id> path; otherwise use cwd from the environment the user is working in.
  2. Claude Code: the UserPromptSubmit hook may already have started the server when the prompt begins with /swe-dashboard (see hooks/dashboard-on-prompt.sh). If so, tell the user to open http://127.0.0.1:47822/ (or SWE_DASHBOARD_PORT if set). If the port is still free, start the server as below.

Read the full file on GitHub · 57 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. 7d ago First seen · 57 lines · 23 tokens per session scan A 5d3b744a021e

Subscribe to this mod's changes

swe-dashboard is a command published in the GitHub repository agentic-swe/agentic-swe (5 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 1,170 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.