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 commands/shipwithai/shipwithai-plugins/ui-distillgit clone --depth 1 https://github.com/ShipWithAI/shipwithai-pluginsWrote 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/commands/shipwithai/shipwithai-plugins/ui-distill)<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>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 | $0.00043 | $0.00966 |
| Opus 5 | $0.00022 | $0.00483 |
| Sonnet 5 | $0.00009 | $0.00193 |
| Haiku 4.5 | $0.00004 | $0.00097 |
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.
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 inTier1Assertions.kt(or tag criticalTextwithModifier.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 intocore:designsystem(+ catalog entry perdocs/components/, + golden), or tighten a Konsist rule inArchitectureTest.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-mechanizablespacing): add ONE concise line to.claude/skills/mobile-design/SKILL.md. Keep it minimal — soft guidance is a staging area, not storage.
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.
- 5d ago First seen · 48 lines · 43 tokens per session scan A 9c64ba294674
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.
Other commands, from other repositories
debug
Systematic debugging with hypotheses and evidence gathering.
whats-next
Show current project status and suggest next steps.
review
Run a Codex code review of your working tree or a branch (read-only).
explore
Fast codebase exploration with Antigravity's agy CLI (Gemini 3.7 Flash, read-only). EXPERIMENTAL.
specmanager-build
Build one phase of a SpecManager feature's plan via the builder subagent. Stops at the phase boundary; never advances.
review-skills
Review changed skills: automated bash checks + 9 structural dimensions (D1-D9) + 5 intent checks (M1-M5). PASS/FAIL verdict. Fix in-place.