ui-distill

ui-distill is a command for coding agents from ShipWithAI/shipwithai-plugins. It costs 43 tokens per session (966 once invoked), scanned A, original, MIT.

A command that reviews repeated findings in a feedback record and proposes turning them into permanent checks or other project changes.

In plain words
What is it for?
Use it to analyze the feedback ledger, review promotion proposals, and apply only the improvements a human approves.
Why use it?
It helps separate one-off advice from problems that happen often enough to deserve an automated safeguard, while keeping a person in control of changes.

Command

Part of the shipwithai-mobile-ui-harness plugin — 2 skills, 3 commands, 1 agent shipped together

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 commands/shipwithai/shipwithai-plugins/ui-distill
Clone the repo
git clone --depth 1 https://github.com/ShipWithAI/shipwithai-plugins

Or install shipwithai-mobile-ui-harness, the plugin that ships this one along with the rest of its 2 skills, 3 commands, 1 agent.

Wrote 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.

agentmods badge for ui-distill

README.md
[![agentmods](https://agentmods.dev/badge/commands/shipwithai/shipwithai-plugins/ui-distill.svg)](https://agentmods.dev/commands/shipwithai/shipwithai-plugins/ui-distill)
Your own site
<a href="https://agentmods.dev/commands/shipwithai/shipwithai-plugins/ui-distill"><img src="https://agentmods.dev/badge/commands/shipwithai/shipwithai-plugins/ui-distill.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 966 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 5.1 $0.00043 $0.00966
Opus 5 $0.00022 $0.00483
Sonnet 5 $0.00009 $0.00193
Haiku 4.5 $0.00004 $0.00097

Measured 5d ago against content hash 9c64ba294674, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ui-distill 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 5d 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.

plugins/mobile-ui-harness/commands/ui-distill.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Turn recurring ledger findings into permanent gates. The deterministic part (cluster → threshold → map to the durability ladder) is the script; the judgment part (approve → implement → delete soft guidance) is you + the human. Never auto-implement a promotion — approval gates everything.

1. Analyze (deterministic)

python3 harness/bin/distill_ledger.py $ARGUMENTS    # writes harness/ledger/promotions.md

Read harness/ledger/promotions.md. Each candidate is a category seen ≥ threshold (default 3) times, with its durability-ladder rung + concrete deposit, breadth (screens/configs), and sample findings.

If there are no candidates over threshold, report the watchlist and stop — nothing has recurred enough to harden yet.

2. Propose to the human (approval required)

Present each candidate: category, count/breadth, the recommended deposit, and 2–3 sample findings. Human approval is required for every Tier-2/3 deposit (a new assertion, a Konsist rule, a component, an API change). Surface them; do not implement anything yet. Let the human pick which to promote (and they may downgrade a rung — e.g. "keep it a rubric line for now").

3. Implement the approved deposit — push it as far down the ladder as it goes

Per the candidate's rung:

  • T2 gate (touch-target, zero-size, out-of-bounds, insets, overflow, truncation, contrast): add/extend the deterministic assertion in Tier1Assertions.kt (or tag critical Text with Modifier.testTag("noTruncate")). Verify it bites: run an inspection test that exhibits the finding and confirm Tier-1 now fails on it, then fix so it passes.
  • T3 structural (reuse, raw-material3, hardcoded values): either promote the reinvented component into core:designsystem (+ catalog entry per docs/components/, + golden), or tighten a Konsist rule in ArchitectureTest.kt. Verify the gate fails on a planted violation (the negative-test discipline from the Konsist work).
  • T1 soft (color, typography, hierarchy, affordance, state, non-mechanizable spacing): add ONE concise line to .claude/skills/mobile-design/SKILL.md. Keep it minimal — soft guidance is a staging area, not storage.

Read the full file on GitHub · 48 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. 5d ago First seen · 48 lines · 43 tokens per session scan A 9c64ba294674

Subscribe to this mod's changes

ui-distill is a command published in the GitHub repository ShipWithAI/shipwithai-plugins (10 stars, last pushed 23d ago), licensed MIT. It adds 43 tokens to every session and 966 once invoked, about $0.0002 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.