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 gabonio/agent-operator-toolkit --skill start-new-appgit clone --depth 1 https://github.com/gabonio/agent-operator-toolkitWrote 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/gabonio/agent-operator-toolkit/start-new-app)<a href="https://agentmods.dev/skills/gabonio/agent-operator-toolkit/start-new-app"><img src="https://agentmods.dev/badge/skills/gabonio/agent-operator-toolkit/start-new-app/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/gabonio/agent-operator-toolkit/start-new-app"><img src="https://agentmods.dev/badge/skills/gabonio/agent-operator-toolkit/start-new-app.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 | $0.00062 | $0.00430 |
| Opus 5.5 | $0.00025 | $0.00172 |
| Sonnet 5.5 | $0.00012 | $0.00086 |
| Haiku 4.5 | $0.00006 | $0.00043 |
Grade A, and why
start-new-app 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 6d 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.
What it actually says
Start New App
- Resolve profiles. Ask one plain-language question at a time, only about unknowns that change the design: users/outcomes, data/growth, platform, integrations, trust boundaries, local development, deployment, ownership, and prototype limits. When the stack is undecided or reconsideration is requested, use the conditional stack-selection interview; otherwise preserve the established stack.
- Use lens routing for relevant product and engineering questions, then turn answers into decisions.
- Design cohesive capability modules and developer navigation, scaled to the app's complexity. Follow develop-from-spec; require explicit approval of the proposed stack and plan before scaffolding. Load only standards matching the approved stack.
- For specialized platform work, delegate through external capability routing. Deployment is separate and requires explicit authorization naming the application and environment.
- Establish and verify a production-like local run path. Scaffold only the approved minimum, include relevant ownership/test/navigation acceptance criteria, and report deferred hardening and handoff gaps.
- Add AGENTS.md or CLAUDE.md guidance only with explicit permission; merge without overwriting existing rules.
Prototype projects must also read prototype delivery. Never present a prototype as production-ready.
What ships with it
1 file 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.
- 6d ago Changed · -1 lines ab81585153b5
- 1mo ago First seen · 18 lines · 62 tokens per session scan A 9891bbd23eb3
start-new-app is a skill published in the GitHub repository gabonio/agent-operator-toolkit (1 stars, last pushed 7d ago), licensed MIT. It adds 62 tokens to every session and 430 once invoked, about $0.0002 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…