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/corezoid/simulator-ai-plugin/simulator-smart-forms-runtimenpx skills add corezoid/simulator-ai-plugin --skill simulator-smart-forms-runtimegit clone --depth 1 https://github.com/corezoid/simulator-ai-pluginWhat 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 | $0.00216 | $0.02785 |
| Opus 5 | $0.00108 | $0.01392 |
| Sonnet 5 | $0.00043 | $0.00557 |
| Haiku 4.5 | $0.00022 | $0.00279 |
Grade A, and why
simulator-smart-forms-runtime 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.
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simulator.Company Smart Form Runtime
You drive an existing Smart Form to completion on the user's behalf — gathering inputs
from the conversation (and any attached document), filling each page's forms, and walking the
flow step by step. You do not build or edit Smart Forms — that is the
simulator-smart-forms author skill.
A Smart Form is a server-driven UI state machine. Corezoid (its backend process) supplies the data, validation, control flow, and side effects (creating actors, running transactions). Your job is the part Corezoid and the GUI can't do: turn an unstructured request into the right field values, ask only for what's genuinely missing, confirm before irreversible steps, and report the result.
Read these references when driving:
$CLAUDE_PLUGIN_ROOT/docs/user-flows/cdu-page-protocol.md— theget/sendprotocol, the Page → Grid → Form → Section → Item model, the component catalogue (§5), and the change protocol (§7). This is the contract you speak.$CLAUDE_PLUGIN_ROOT/docs/user-flows/app-catalog.md— how to discover which app to run (match intent against each Smart Form's nativetitle+description; tags / linked actors for scope). No custom catalog format.
Tools you use
| Step | Tool(s) |
|---|---|
| Discover the app | filterActors (over the scripts system form) → match intent against each actor's title + description (tags / getRelatedActors to scope); or getActorByRef when the user names it |
| Render a page | appGetPage (accId, ref, envTitle, page, query) |
| Submit a form | appSendForm (accId, ref, envTitle, page, formId, buttonId, data, query) |
| Read an attached document | readAttachment |
| Report a result | buildLink (deep-link to a created actor/record) |
These two — appGetPage / appSendForm — are universal: the same two tools drive every
Smart Form. Nothing about the app is hard-coded; you interpret what the page returns.
The drive loop
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.
- 2d ago First seen · 204 lines · 216 tokens per session scan A 1b5916d300a2
simulator-smart-forms-runtime is a skill published in the GitHub repository corezoid/simulator-ai-plugin (60 stars, last pushed 5d ago), licensed MIT. It adds 216 tokens to every session and 2,785 once invoked, about $0.0011 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
unslop
Humanize LLM output so it reads like a careful human wrote it. Subtracts AI-isms (sycophancy, tricolons, em-dash overuse, "delve"/"tapestry"/"testament", hedging stacks, tidy five-paragraph shapes), engineers burstiness and calibrated uncertainty, and preserves technical accuracy. Supports intensity levels: subtle…
unslop-file
Humanize natural-language memory files (CLAUDE.md, todos, preferences, docs) by removing AI-isms and adding burstiness while preserving every code block, URL, path, command, and heading exactly. Two modes: --deterministic (fast, regex-based, no API) and LLM (default, calls Claude for rewrite). Humanized version…
unslop-commit
Rewrites commit messages so they sound like a careful human engineer wrote them. Strips AI/marketing slop ("comprehensive solution", "robust implementation", "leverage", "enhance", "seamlessly", "This commit..."). Keeps Conventional Commits format. Subject ≤72 chars (aim ≤50), imperative mood. Body only when "why"…
unslop-help
Quick-reference card for unslop modes, sub-skills, and slash commands. One-shot display, not a persistent mode. Trigger: /unslop-help, "unslop help", "what unslop commands", "how do I use unslop".
unslop-reasoning
Strip AI-slop patterns from reasoning traces (chain-of-thought, extended thinking, agent decomposition) — not final prose. Reasoning text has its own slop catalog that regular unslop doesn't target: over-explaining the question, over-hedging, over-decomposing trivial problems into 6-bullet substeps, infinite-loop…
unslop-review
Rewrites code review comments so they read like a human teammate wrote them. Cuts corporate-AI throat-clearing ("I noticed...", "I was wondering if perhaps...", "It might be worth considering..."). Each comment is direct: location, the issue, a concrete fix. Use when user says "humanize review", "de-slop PR comment"…