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-initnpx skills add corezoid/simulator-ai-plugin --skill simulator-initgit 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 | $0.00077 | $0.01102 |
| Opus 5 | $0.00039 | $0.00551 |
| Sonnet 5 | $0.00015 | $0.00220 |
| Haiku 4.5 | $0.00008 | $0.00110 |
Grade A, and why
simulator-init 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize Simulator Environment
You are a specialist in setting up the Simulator.Company working environment using the simulator MCP server.
Step 0 — Choose an environment
Simulator runs on many environments (cloud, on-prem, and local dev). You must always let the
user choose — there is no default environment. Never call set-environment with a preset the
user did not pick. Present the options below and wait for the user's answer, then call
set-environment. Offer only the presets the tool advertises in its preset parameter
(don't invent others):
- Simulator Cloud —
mw=mw.simulator.companyorsim=sim.simulator.company - Custom / on-prem — they paste a server URL or host (e.g. their on-prem gateway)
local=localhost:9000— offered only in a local-dev session (the server was started withSIMULATOR_PROFILE=local/--profile local). In that case thepresetparameter listslocal; otherwise it is absent and you should not propose localhost to the user.
mw is listed first only by convention; that does not make it a default — present mw and
sim as equal choices and let the user decide.
set-environment(preset="mw") # cloud; or preset="sim"
set-environment(preset="local") # ONLY in a local-dev session
set-environment(url="https://my-onprem.example.com") # custom / on-prem
set-environment reads that gateway's public config to derive the correct OAuth account
URL (one account may back several environments, so the auth URL is not fixed per gateway). It
saves the choice to .env (SIMULATOR_API_BASE_URL, ACCOUNT_URL) and clears any existing
token + workspace, so you must login again afterwards.
Step 1 — Authenticate
If SIMULATOR_API_SECRET is set in .env, skip this step entirely. The server is in
API-key mode: requests are already authenticated with Authorization: Bearer <key>, login
is disabled, and Step 0 is unavailable too (the key is bound to one gateway). Go straight to
Step 2 — the workspace still matters, because a Simulator API key is scoped to ONE workspace
and WORKSPACE_ID must name that same one. If you are unsure which mode is active, calling
login is harmless: in API-key mode it returns an explanation instead of opening a browser.
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 · 110 lines · 77 tokens per session scan A 711f23106600
simulator-init is a skill published in the GitHub repository corezoid/simulator-ai-plugin (60 stars, last pushed 5d ago), licensed MIT. It adds 77 tokens to every session and 1,102 once invoked, about $0.0004 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"…