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 edwardyen724-g/david-vscode --skill create-dashboardgit clone --depth 1 https://github.com/edwardyen724-g/david-vscodeWrote 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/edwardyen724-g/david-vscode/create-dashboard)<a href="https://agentmods.dev/skills/edwardyen724-g/david-vscode/create-dashboard"><img src="https://agentmods.dev/badge/skills/edwardyen724-g/david-vscode/create-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.
<a href="https://agentmods.dev/skills/edwardyen724-g/david-vscode/create-dashboard"><img src="https://agentmods.dev/badge/skills/edwardyen724-g/david-vscode/create-dashboard.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 | $0.00112 | $0.02771 |
| Opus 5.5 | $0.00045 | $0.01108 |
| Sonnet 5.5 | $0.00022 | $0.00554 |
| Haiku 4.5 | $0.00011 | $0.00277 |
Grade A, and why
create-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 2mo 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
create-dashboard — design and write a project dashboard for this David project
You are running this skill as the David Overseer (or a designated analytics worker). Your goal: produce a valid dashboards/<name>.json in this workspace, stub its data/* sources so it renders immediately (not broken), and either propose a populate-job or hand the data-population to an agent.
How this differs from create-agent / create-job
create-agent and create-job end with an events.jsonl append (create_agent / create_job) that David's plugin acts on. Dashboards have NO plugin event — the F022 dashboardsStore simply reads dashboards/*.json and data/* from the workspace, and the david.dashboards view + webview render them. So in this skill you write the dashboard JSON file directly with the Write tool. That is the intended path, not a fallback.
Hard rules
- The dashboard is only useful if its data sources exist. After writing
dashboards/<name>.json, you MUST also stub everysourcefile it references with a valid, parseable starter (empty object/array/markdown as appropriate). A widget pointing at a missing file renders as—/ "(no rows)" — acceptable, but stub them so the first open looks intentional. - Real, measurable metrics only. Never invent a metric the project can't actually produce. If a metric needs data nobody is writing yet, either (a) propose a populate-job/agent that will write it, or (b) drop it. No fabricated or estimated numbers. (See the honesty mandate in the project's long-term memory.)
- Do NOT hardcode metric-selection or visual design in this skill. Those plug in from the two design specs (slots below). If a spec isn't present yet, use the documented interim default AND tell the user the dashboard will improve once the spec lands.
- Ask before writing. Show the proposed dashboard (Step 4) and get approval before Step 5 writes files. create-agent-style conversational pacing — don't dump everything at once.
- Write only inside this workspace under
dashboards/anddata/. Don't touch product code or other agents' files.
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.
- 2mo ago First seen · 138 lines · 112 tokens per session scan A 5a2deb995171
create-dashboard is a skill published in the GitHub repository edwardyen724-g/david-vscode (2 stars, last pushed 4mo ago), licensed MIT. It adds 112 tokens to every session and 2,771 once invoked, about $0.0004 per session on Opus 5.5. 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
autonomous
Run multiple phases hands-free. Chains discuss, plan, build, and verify automatically.
quick
Execute an ad-hoc task with atomic commits. Skips full plan/review.
debug
Systematic debugging with hypothesis testing. Persistent across sessions.
resume
Pick up where you left off. Restores context and suggests next action.
audit
Review past Claude Code sessions for PBR workflow compliance and UX quality.
config
Configure settings: depth, model profiles, features, git, and gates.