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-tasksnpx skills add corezoid/simulator-ai-plugin --skill simulator-tasksgit 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 | $0.00404 | $0.03573 |
| Opus 5 | $0.00202 | $0.01786 |
| Sonnet 5 | $0.00081 | $0.00715 |
| Haiku 4.5 | $0.00040 | $0.00357 |
Grade A, and why
simulator-tasks 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 3d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Curated tool names (v2 server):
getForms,searchUsers,getUsers,createActor,getActorByRef,filterActors,saveAccessRules,getAccessRules,createReaction,getReactions. Call them by these exact names. There is no dedicated "create task" / "assign" tool — a task is composed from these.
Simulator.Company Task Specialist
In Simulator.Company a task is an actor of the Events system form with no
chatType (an empty/absent chatType is what separates a task / plain event from a
chat). The Events form is the same one used for calendar events, SIP meetings, and chats
— chatType is what disambiguates them.
Orders / directives are tasks. A request to create an order / directive document aimed at a person — «створи наказ на Салімова про …», «склади розпорядження для …», "create an order for X to …", ru «приказ на …» — is a task, not a plain event. The addressee ("на <кого>" / "for ") is the executor: create the Events actor, then grant that person
executeviasaveAccessRules(step 4 below). Putting the name only in the title/description is the common mistake — without theexecuterule the person is not assigned and gets nodoneaction. Resolve the addressee'suserIdwithsearchUsersfirst; if other people are named to approve/sign, give themsign/ds.If the workspace has a dedicated «наказ»/order form (with example documents), mirror an example — don't just
createActorand stop. Read one existing order of that form (getActor+getAccessRules) and reproduce how it assigns the responsible person: typically anexecuteaccess rule for the addressee (saveAccessRules), and/or a responsible/executor data field on the form (aworkspaceMembersdynamic-select whose value is the user id — see the actordataprotocol). Set whichever the example uses, and always grant the addressee access — an order with no access rule for the person never appears in their events. Creating the actor alone is not "assigned".
A task's roles are access privileges on the task actor, not data fields:
| Role | Privilege | How they act on the task |
|---|---|---|
| Executor / assignee (виконавець) | execute |
Marks the work complete with a done reaction |
| Approver (хто погоджує) | sign |
Approves with a sign reaction, or declines with reject |
| Legal-document signer (підпис на юр. документі) | ds |
Applies a qualified digital signature with a ds reaction |
| Watcher | view only |
Can see the task; no action |
viewis implied when any other privilege is set. One person can hold several roles (e.g.{execute:true, sign:true}) — that's one rule with both flags. Different people get separate rules.
There is no server-side "a task must have an executor / must be approved in order"
enforcement — a task is composed from createActor + saveAccessRules + reactions,
and this skill owns that discipline.
Read
$CLAUDE_PLUGIN_ROOT/docs/entities/tasks.mdfor the full model, andchats.mdfor the shared Events-form field list.
Reply to the user in their own language.
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.
- 3d ago First seen · 246 lines · 404 tokens per session scan A d11c5ab3b2ed
simulator-tasks is a skill published in the GitHub repository corezoid/simulator-ai-plugin (60 stars, last pushed 6d ago), licensed MIT. It adds 404 tokens to every session and 3,573 once invoked, about $0.0020 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"…