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-agentsnpx skills add corezoid/simulator-ai-plugin --skill simulator-agentsgit 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 | $0.00519 | $0.02911 |
| Opus 5 | $0.00260 | $0.01456 |
| Sonnet 5 | $0.00104 | $0.00582 |
| Haiku 4.5 | $0.00052 | $0.00291 |
Grade A, and why
simulator-agents 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Curated tool names (v2 server):
findAgent,getAgent(the agent registry — user twins by default, any registry form viaformId);searchUsers,getUsers,getSystemActor(resolve people/twins);searchActors,getActor(resolve non-user agent actors). Delegation reuses thesimulator-chatflow (p2p message) and thesimulator-tasksflow (create + assign a task) — there is no dedicated "delegate" tool; the outcome is composed from these.
Simulator.Company Digital-Twin & Actor-Agent Specialist
An agent is any actor whose description holds an "# Agent" competency profile —
System instructions (persona + rules) plus Knowledge (competency profile, durable facts, recent
activity) — describing what it does, what it knows, and whether it fits a task.
The common case is a person. Every workspace user has a 1:1 twin actor (isSystem=true,
systemObjType="user", systemObjId=<userId>, on the System system form, title = nick) whose
profile a factory generates from git activity. But the profile can live on any actor:
- a non-user system actor on the
Systemform (a service/bot/device twin); - a plain actor on a business form (a team, a department, an organization, a process, a service).
So an agent actor is a skill actor, and this skill is the actor-analog of simulator-skills:
the registry is the set of agent actors instead of the Skills form. Talking to an agent "as an
agent" means: discover it (findAgent) → load its profile (getAgent) → adopt it as the
persona → answer, or act, or delegate.
Reply to the user in their own language.
Workspace check
These tools operate in a workspace. If the active workspace (accId) is unknown, ask the user
for it in their own language (or suggest /simulator-init). If findAgent/getAgent reports
the System form is missing, the backend system-forms sync has not run for this workspace — tell
the user. (That only affects the default user-twin registry; a non-user registry addressed by
formId does not need the System form.)
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 · 156 lines · 519 tokens per session scan A c1211e459678
simulator-agents is a skill published in the GitHub repository corezoid/simulator-ai-plugin (60 stars, last pushed 5d ago), licensed MIT. It adds 519 tokens to every session and 2,911 once invoked, about $0.0026 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"…