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 skills/andreaserradev-gbj/dev-workflow/dev-dashboard-tuinpx skills add andreaserradev-gbj/dev-workflow --skill dev-dashboard-tuigit clone --depth 1 https://github.com/andreaserradev-gbj/dev-workflowWrote 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/andreaserradev-gbj/dev-workflow/dev-dashboard-tui)<a href="https://agentmods.dev/skills/andreaserradev-gbj/dev-workflow/dev-dashboard-tui"><img src="https://agentmods.dev/badge/skills/andreaserradev-gbj/dev-workflow/dev-dashboard-tui.svg" alt="Measured on agentmods" 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 | $0.00090 | $0.00702 |
| Opus 5 | $0.00045 | $0.00351 |
| Sonnet 5 | $0.00018 | $0.00140 |
| Haiku 4.5 | $0.00009 | $0.00070 |
Grade A, and why
dev-dashboard-tui 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 4d 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.
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.
Launch the Dev Dashboard TUI
The dev-dashboard TUI is the terminal-native sibling of the web /dev-dashboard:
the same cross-project .dev/ feature portfolio — a recency-sorted project rail,
per-feature status and progress, and a detail pane — rendered natively in the
terminal for SSH/tmux/no-browser workflows. It live-refreshes as .dev/ PRDs
change.
Why the agent cannot start it
A TUI is a foreground, interactive process that must own a real terminal
(TTY). Claude Code's Bash tool runs commands against a detached, non-interactive
pipe — an Ink app rendered there produces garbage and never receives keystrokes.
Unlike /dev-dashboard (which backgrounds an HTTP server and reports a URL), this
skill hands the launch command to the user to run in their own terminal.
Do not attempt to spawn the TUI from a Bash tool call.
Step 1: Resolve the launch command
The launcher lives at scripts/launch.sh within this skill's directory. Build the
absolute path to it (call it $LAUNCH). Optionally confirm the bundled artifact
is present first:
test -f "$LAUNCH" && echo ok
Where $LAUNCH is the absolute path to scripts/launch.sh within this skill's
directory. Use $HOME instead of literal home paths.
Step 2: Tell the user to run it
Present the exact command for the user to paste into their own terminal (with
$LAUNCH resolved to the real absolute path):
bash "<absolute path>/scripts/launch.sh"
To scan a specific directory instead of the stored config / current directory,
they can append --scan <dir>:
bash "<absolute path>/scripts/launch.sh" --scan ~/code
launch.sh resolves the bundled tui/cli.mjs relative to its own location and
exec nodes it in the foreground — no port, no background process, nothing to
stop afterwards. Requires node (>= 24).
Step 3: Keybindings
Once it opens:
j/kor↑/↓— move the selection within the focused paneh/lor←/→— move focus across the panes (rail → list → detail)Tabor1–6— switch the status filterSpace— toggle the session-history detailqorCtrl+C— quit (restores the terminal cleanly)
What ships with it
2 files 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.
- 4d ago First seen · 76 lines · 90 tokens per session scan A 2474ca24c1e3
dev-dashboard-tui is a skill published in the GitHub repository andreaserradev-gbj/dev-workflow (2 stars, last pushed 6d ago), licensed MIT. It adds 90 tokens to every session and 702 once invoked, about $0.0005 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 skills, from other repositories
cat:decompose-task
Split oversized task into smaller tasks with proper dependency management.
cat:run-retrospective
Run scheduled retrospective analysis, derive action items, and track effectiveness.
director:status
See your project progress at a glance.
gsd-new-milestone
Start a new milestone cycle update PROJECT.md and route to requirements.
gsd-execute-phase
Execute all plans in a phase with wave-based parallelization.
gsd-new-project
Initialize a new project with deep context gathering and PROJECT.md.