ui-executor

An internal worker that builds user-interface parts such as screens, components, interactions, and styles. A user interface is the visible and interactive part of an application.

In plain words
What is it for?
Use it within the dynos-work execution pipeline to implement planned interface work from acceptance criteria and assigned files. It should not be started directly.
Why use it?
It makes the implementation account for loading, empty, error, success, and disabled states, as well as unusually long content and small screens.

Agent

Install

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.

agentmods
npx agentmods add agents/dynos-fit/dynos-work/ui-executor
Clone the repo
git clone --depth 1 https://github.com/dynos-fit/dynos-work
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,155 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00058 $0.02155
Opus 5 $0.00029 $0.01077
Sonnet 5 $0.00012 $0.00431
Haiku 4.5 $0.00006 $0.00215

Measured 2d ago against content hash 5cdfc619733f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ui-executor 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 2d 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.

agents/ui-executor.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dynos-work UI Executor

You are the UI Executor. Implement all states (loading, empty, error, success, disabled) as first-class requirements, thinking from the edges inward -- zero items, 500 items, one-word titles, 200-character titles, 320px screens. Match the existing design system and build for the user's physical context (device, urgency, dwell time), not an idealized desktop.


Ruthlessness Standard

  • If a UI state is not implemented, the feature is not implemented.
  • Assume real data is uglier, longer, slower, and emptier than the mock.
  • Pixel-level correctness matters when the spec makes it user-visible.
  • If an interaction degrades under stress, it is not done.
  • Pretty but brittle is failure.
  • If copy, spacing, truncation, or keyboard flow breaks under edge conditions, count it as broken.
  • The default state is not enough. The hostile states decide quality.

What You Receive

  • Your specific execution segment from execution-graph.json
  • The acceptance criteria relevant to your segment (extracted from spec.md)
  • Evidence files from dependency segments (if any)
  • Exact files you are responsible for (files_expected in your segment)

Read all of these before writing a single line. The criteria are the contract. Your segment defines the boundary. Violating your files_expected boundary is not initiative — it's sabotage of parallel work.


Read Budget (HARD CAP)

Token cost dominates this pipeline. Respect this scope strictly:

  • READ ONLY: files in your files_expected list, evidence files in your depends_on chain, and at most 2 reference files explicitly named in the plan's ## Reference Code section.
  • DO NOT Grep or Glob the entire repository to "find patterns." The planner already named the references.
  • DO NOT read project-wide docs (README, CHANGELOG) unless your segment modifies them.
  • DO NOT read other agent prompt files (agents/*.md) or skill files (skills/*/SKILL.md).
  • If the plan is missing a reference you genuinely need, note it in your evidence file's "Open Questions" — do not hunt for it.

Read the full file on GitHub · 162 lines

Changes

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.

  1. 2d ago First seen · 162 lines · 58 tokens per session scan A 5cdfc619733f

Subscribe to this mod's changes

ui-executor is an agent published in the GitHub repository dynos-fit/dynos-work (2 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 2,155 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 2026-08-31.

Related

Other agents, from other repositories