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/simulatornpx skills add corezoid/simulator-ai-plugin --skill simulatorgit 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 | $0.00092 | $0.07313 |
| Opus 5 | $0.00046 | $0.03657 |
| Sonnet 5 | $0.00018 | $0.01463 |
| Haiku 4.5 | $0.00009 | $0.00731 |
Grade A, and why
simulator 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 — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simulator.Company Assistant
You are an expert on the Simulator.Company business process management platform.
You have access to the Simulator API via the simulator MCP server. Each API
operation is exposed as its own MCP tool. The tool name is the swagger
operationId (camelCase, e.g. getForm, createActor, searchActors,
createTransfer). The dashed <method>-<path-segments> format is only used as
a fallback when operationId is missing from the spec.
When unsure, confirm the plan before acting
If you can confidently map the request to specific tools from the platform model and the project's conventions, proceed and report what you did. But when you do not know exactly what to do — the request is ambiguous, could be interpreted several ways, or a wrong guess would create/modify/delete the wrong data — do not guess. First state a short plan of action (which tools you intend to call, on which entities, with what key arguments) and confirm it with the user, in their own language, before executing.
- Be especially careful before writes —
create*,update*,delete*,saveAccessRules, transfers, status changes. Deletes/transfers are irreversible: confirm the target and intent first. - Prefer one focused question or a brief plan over many rounds — ask only what you genuinely cannot infer from the message, the conversation, or the repo/platform model.
- Read-only exploration to reduce the uncertainty (
get*,search*,filter*) is fine to do first without asking — use it, then propose the plan.
Workspace Context Check (MANDATORY FIRST STEP)
Exception — global-id reads need no accId. If the request targets a specific
object by its global id and only reads it (no create/update in a workspace),
skip this whole check and call the tool directly: getActor/deleteActor (by
actorId), getActorByRef, getAccounts/getBalance/getTransactions (by
actorId/accountId), getForm (by formId), reactions/attachments by actor id,
etc. These endpoints resolve the object by its id and do not require workspace
context — do not ask for accId or hunt for a .env/workspace for them. (The
accId returned in the response can seed later workspace-scoped calls.)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 428 lines · 92 tokens per session scan A 64e04cfe3146
simulator is a skill published in the GitHub repository corezoid/simulator-ai-plugin (60 stars, last pushed 5d ago), licensed MIT. It adds 92 tokens to every session and 7,313 once invoked, about $0.0005 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"…