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-attachmentsnpx skills add corezoid/simulator-ai-plugin --skill simulator-attachmentsgit 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 | $0.00145 | $0.01154 |
| Opus 5 | $0.00072 | $0.00577 |
| Sonnet 5 | $0.00029 | $0.00231 |
| Haiku 4.5 | $0.00015 | $0.00115 |
Grade A, and why
simulator-attachments 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Curated tool names (v2 server):
uploadBase64,getAttachments,getActorAttachments,addAttachments,updateAttachment,removeAttachments. Plus the engine toolsuploadActorPicture/uploadActorPictureBulkfor actor avatars. Call them by these exact names.
Simulator.Company Files & Attachments Specialist
A file is uploaded once into the workspace and becomes an attachment record (with an
attachId). You then link that record to actors or reactions. Listing, renaming and
unlinking operate on the record.
Relationship to the other skills
simulator-reactions— a comment can carry files via itsattachments:[{attachId}].simulator-actors—uploadActorPicturesets an actor's avatar (an engine tool, not here).
The flow: upload → attachId → link
- Upload the bytes → get the attachment record (
attachId, storedfileName). - Link the
attachIdto an actor/reaction (or pass it in a reaction'sattachments). - Manage it later (rename, list, unlink).
Workspace context
uploadBase64, getAttachments, addAttachments, removeAttachments take an accId
(workspace id) — it defaults to the configured workspace if omitted. updateAttachment
is addressed by attachId only.
Upload a file
uploadBase64(
accId="ws_xxx", # optional — defaults to the configured workspace
file="<base64 string>", # prefer RAW base64; a data:<mime>;base64, prefix is also stripped server-side
originalName="report.pdf", # sets the type + title
ttl=0) # seconds; 0 = permanent
# → returns the attachment record incl. attachId + fileName
Prefer raw base64. A
data:URI prefix is accepted and stripped server-side, but raw base64 is the safe default. Multipart uploads are not a curated tool — useuploadActorPicturefor actor images, oruploadBase64for everything else.
Link / unlink files
addAttachments(accId="ws_xxx", items=[
{ "attachId": 5521, "actorId": "<actor or reaction UUID>" }
])
removeAttachments(accId="ws_xxx", items=[
{ "attachId": 5521, "actorId": "<actor or reaction UUID>" }
]) # unlinks; does NOT delete the stored file
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 · 104 lines · 145 tokens per session scan A 9c3c6231d76d
simulator-attachments is a skill published in the GitHub repository corezoid/simulator-ai-plugin (60 stars, last pushed 5d ago), licensed MIT. It adds 145 tokens to every session and 1,154 once invoked, about $0.0007 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"…