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-jobgit 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-job)<a href="https://agentmods.dev/skills/edwardyen724-g/david-vscode/create-job"><img src="https://agentmods.dev/badge/skills/edwardyen724-g/david-vscode/create-job/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-job"><img src="https://agentmods.dev/badge/skills/edwardyen724-g/david-vscode/create-job.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 | $0.00097 | $0.01515 |
| Opus 5 | $0.00048 | $0.00758 |
| Sonnet 5 | $0.00019 | $0.00303 |
| Haiku 4.5 | $0.00010 | $0.00152 |
Grade A, and why
create-job 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 10d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
create-job — design and register a new scheduled Job for this David project
You are running this skill as the David Overseer. Your goal is to produce a single, well-shaped events.jsonl append call with type: "create_job" at the end. Do not write files manually — David's plugin handles the on-disk job config AND the launchd plist when it receives the structured event.
Hard rules
- You MUST end this conversation with exactly one
events.jsonl appendcall of type"create_job". Until you do, no job exists. - DO NOT use Edit/Write to create
jobs/<name>.jsonor write a~/Library/LaunchAgents/com.david.*.plist. The plugin owns those files atomically. - Ask one question at a time. Don't dump the whole questionnaire.
Workflow
Step 0: Acknowledge + check for overlap
If the user's request would create a duplicate-purpose job, surface that.
Step 1 — Trigger (1 / 5)
Ask:
scheduled— fires on a recurring scheduleon-demand— only when you click "Run job" or an agent invokes itboth— scheduled AND can be manually triggered (this is automatic; scheduled jobs can always also be run manually)
Step 2 — Schedule (2 / 5) — only if scheduled
Accept natural language. Translate to cron yourself. Examples:
| User says | Cron |
|---|---|
| "every day at 9am" | 0 9 * * * |
| "every weekday at 9am" | 0 9 * * 1-5 (but David's v0.1 cron parser only supports fixed integers, not ranges — for weekday-only, use a different mechanism or run daily and let the script no-op on weekends) |
| "every Monday at 8am" | 0 8 * * 1 |
| "every Sunday at 8am" | 0 8 * * 0 |
| "every hour" | 0 * * * * |
KNOWN LIMITATION (v0.1): David's cron-to-launchd converter only supports FIXED INTEGERS and *. Lists (1,3,5), ranges (1-5), and steps (*/5) will fail at plist registration. If the user wants weekday-only or every-N-hours, tell them the limitation and either pick a fixed equivalent or have the script handle the filtering internally (run daily, exit early on wrong day).
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.
- 10d ago First seen · 119 lines · 97 tokens per session scan A 566282d36477
create-job is a skill published in the GitHub repository edwardyen724-g/david-vscode (2 stars, last pushed 3mo ago), licensed MIT. It adds 97 tokens to every session and 1,515 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
tmux-layout
Use this skill when the operator wants a prepared tmux visualization layout for the session's side-channels (STATE.md tail, CI-watch, events.jsonl tail). Renders a 4-pane default layout or debug layout. Read-only side-channel observability — the coordinator chat stays in the operator's original terminal. Trigger…
autonomous
Run multiple phases hands-free. Chains discuss, plan, build, and verify automatically.
resume
Pick up where you left off. Restores context and suggests next action.
continue
Execute the next logical step automatically. No prompts, no decisions — just do it.
do
Route freeform text to the right PBR skill automatically.
note
Zero-friction idea capture. Append, list, or promote notes to todos.