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-agentgit 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-agent)<a href="https://agentmods.dev/skills/edwardyen724-g/david-vscode/create-agent"><img src="https://agentmods.dev/badge/skills/edwardyen724-g/david-vscode/create-agent.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 5.1 | $0.00098 | $0.01984 |
| Opus 5 | $0.00049 | $0.00992 |
| Sonnet 5 | $0.00020 | $0.00397 |
| Haiku 4.5 | $0.00010 | $0.00198 |
Grade A, and why
create-agent 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 8d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
create-agent — design and spawn a new worker agent 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_agent" at the end. Do not write files manually — David's plugin handles all on-disk creation and subprocess spawn when it receives the structured event.
Hard rules
- You MUST end this conversation with exactly one append to your
events.jsonlfile containing a JSON object with"type": "create_agent". Until you do, no agent exists. - DO NOT use Edit/Write tools to create PERSONA.md, LEDGER, NEXT.md, or to modify david-config.json. The plugin owns those files.
- Ask the questions one at a time. Don't dump the whole questionnaire on the user. Conversational pacing.
- If a question is unclear, ask a clarifying question — don't guess. The whole point of this skill is to produce a reliably-shaped agent.
- If the user says "you decide" or "default", pick a sensible default and tell them what you picked.
Workflow
Step 0: Acknowledge + check for overlap
Read david-config.json (it's in this workspace's root) for the current agent roster. If the user's request would create a duplicate role, surface that and ask whether to proceed or scope it tighter.
Open with something like: "Let's design a new agent. I see you already have: [list]. What role do you want this new one to play?"
Step 1 — Role (1 / 6)
Ask the user what the agent will focus on. Offer canonical archetypes:
marketing— drafts, edits, voice consistency, cross-postingresearch— reads sources, extracts findings, citationsops— runs commands, manages deploys, monitorsdesign— UI, copy, brand consistencysupport— answers questions, triages issuesdevops— CI/CD, infra, observabilitycontent— long-form writing, scripts, narrativesanalytics— metrics, dashboards, KPI trackingcustom— they describe in their own words
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.
- 8d ago First seen · 142 lines · 98 tokens per session scan A 10e8633c24fe
create-agent is a skill published in the GitHub repository edwardyen724-g/david-vscode (2 stars, last pushed 3mo ago), licensed MIT. It adds 98 tokens to every session and 1,984 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
claude-md-drift-check
Use when detecting drift between CLAUDE.md (or AGENTS.md, the Codex CLI alias) / meta narrative and live repository state. Ten checks: absolute-path resolution, 01-projects/ count claims, issue-reference freshness, session-file existence, command-count sync, session-config-parity (mandatory template keys = error…
convergence-monitoring
Monitor iterative improvement loops for convergence. Three signals — shrinking diff, pass-rate plateau, velocity — drive a Stop/Continue/Investigate decision at each inter-wave checkpoint. Distinct from /evolve (retrospective) and session-reviewer (wave output review): convergence-monitoring answers "are we making…
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
eval
Use this skill to run an honest session-process evaluation (Standard v1, aiat-llm-eval/1.0) — score the last completed orchestrator session against the pre-registered rubric-v1 dimensions, run /eval, evaluate this session, produce an eval report, or re-verify a stored eval run for reproducibility. Deterministic-first…
evolve
Use this skill when extracting session patterns into reusable learnings. Three modes: analyze (extract from session history), review (edit/manage existing learnings), list (display active learnings). Manages .orchestrator/metrics/learnings.jsonl.
frontmatter-guard
Injects the canonical vault frontmatter schema snippet into agent prompts before any vault-write task, preventing malformed YAML frontmatter in Obsidian notes. Context: wave-executor is about to dispatch a vault-mirror agent that writes learning notes under /Projects/vault/40-learnings/. user: "dispatch vault-write…