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/runvendo/vendo/make-a-screennpx skills add runvendo/vendo --skill make-a-screengit clone --depth 1 https://github.com/runvendo/vendoWrote 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/runvendo/vendo/make-a-screen)<a href="https://agentmods.dev/skills/runvendo/vendo/make-a-screen"><img src="https://agentmods.dev/badge/skills/runvendo/vendo/make-a-screen.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 | $0.00070 | $0.01134 |
| Opus 5 | $0.00035 | $0.00567 |
| Sonnet 5 | $0.00014 | $0.00227 |
| Haiku 4.5 | $0.00007 | $0.00113 |
Grade A, and why
make-a-screen 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Making the person a screen
The connected product exposes one tool for this: vendo_make. It is the only
way to put a screen in front of the person, and you never build UI yourself.
When an answer wants to be looked at
Reach for vendo_make when the honest answer is a shape rather than a sentence:
- more than a handful of rows — you would be reading a table out loud
- a comparison, a trend, or a breakdown — anything with an "over time" or "versus" in it
- something they will come back to — "keep an eye on", "every week", "track"
- something they need to act on — a screen can carry the buttons; your message cannot
Answer in words instead when the answer is words: one number, one status, one fact, a yes or no, or an explanation. A screen for "what's my balance" is worse than saying the balance.
How to phrase request
request is prose — what you would say to a designer sitting next to you. Say
what the person wants, in your own words.
- Do describe the want: "the last three months of spending, broken down by category, with a way to jump into any month"
- Don't describe an implementation: no component names, no layout grids, no JSON, no field names you guessed at
- Don't ask for fonts, colors, or branding — it inherits the product's own
- Don't bake in data. Never paste numbers you looked up or computed ("Total: $4,210"). The screen binds live data itself, and hardcoded figures are rejected as invented
Pass context for background the product cannot see from its side: what they
told you earlier in this conversation, a constraint they mentioned, which of
several things they meant. Free text, a couple of sentences.
Pass app only to change one specific existing app you already have the id
for. Leaving it out lets the product decide whether to continue the last thing
or start something new — which is usually the right call.
Pass slot only when the person names a place in the product and you have
that place's exact id — they said it, or an earlier answer carried it. The screen
then lands in that spot on their own page instead of their apps list. Slot ids
belong to the product, not to you: never invent one. A made-up id puts the
screen somewhere nobody is looking, and nothing about that looks like an error.
No id, no slot — the default destination is always a safe answer.
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 First seen · 92 lines · 70 tokens per session scan A d84c4357cd0f
make-a-screen is a skill published in the GitHub repository runvendo/vendo (604 stars, last pushed 3d ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,134 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
jk
Jenkins CLI for controllers. Use when users need to manage jobs, pipelines, config.xml, runs, logs, artifacts, credentials, nodes, or queues in Jenkins. Triggers include "jenkins", "jk", "pipeline", "build", "job create", "job config", "config.xml", "run logs", "jenkins credentials", "jenkins node".
build-go-stack
Structure, implement, refactor, or review Go backend applications using Fiber, cmd-local composition and HTTP transport, component-owned domain and Mongo persistence, contextual error wrapping with final-boundary logging, concrete types, prefixed environment and optional Vault configuration, dependency inversion…
analyze-proxy-log
Analyze agentpack Claude proxy JSONL diagnostics for hangs, upstream errors, WebSocket setup failures, auth refresh problems, transport fallback, and stalled requests. Use when debugging agentpack --proxy claude, AGENTPACKPROXYLOGDIR, $AGENTPACKHOME/projects//proxy-logs, proxy hangs, proxy errors, or Codex/OpenAI…
migrate-plugins
Migrate community plugins from Claude Code, Codex, or Skills.sh into AgentPlugins. Use when the user wants to convert a plugin they wrote or found into the AgentPlugins v1 manifest format so it can be installed via agentplugins add or agentplugins import.
agent-broom
Remember to run Agent Broom, the script-backed process tracking, audit, and cleanup tool. Use before starting another localhost server, before ending a turn that spawned long-running processes, when CPU/memory is high, when disk is low, or when the user says "what is running", "devclean", "orphaned MCP", "cleanup…
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…