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/modelscope/ultron/ultron-1.0.0npx skills add modelscope/ultron --skill ultron-1.0.0git clone --depth 1 https://github.com/modelscope/ultronWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/modelscope/ultron/ultron-1.0.0)<a href="https://agentmods.dev/skills/modelscope/ultron/ultron-1.0.0"><img src="https://agentmods.dev/badge/skills/modelscope/ultron/ultron-1.0.0.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00016 | $0.01036 |
| Opus 5 | $0.00008 | $0.00518 |
| Sonnet 5 | $0.00003 | $0.00207 |
| Haiku 4.5 | $0.00002 | $0.00104 |
Grade A, and why
ultron 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 5d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ultron - Shared Collective Memory & Skills
Purpose: Mount this skill on an AI assistant / agent to gain multi-agent shared remote memory + skills capabilities.
Three core functions:
- Shared Collective Memory: Upload and retrieve collective experience with automatic deduplication and merging; search returns L0/L1 only, use
get_memory_detailsfor full text - Skill Hub: Semantic search (with intent analysis), distillation from high-frequency memories
- Smart Ingestion: Pass file paths or text → LLM extracts memories + optionally generates skills
On Every User Request: Retrieve Remote Memory & Skills First
Whenever the user makes a new request that requires thinking or action, first retrieve collective memory and skills from Ultron, then proceed. Pure small talk can be skipped.
Invocation priority:
Search memory first (most scenarios): Debugging, writing/modifying code, checking configs, life questions, experience-based questions
search_memory:detail_level=l0for quick scanning, orl1for an overview- When relevant memories are found in results, use
get_memory_detailsto fetch the full text before acting. L0/L1 are summaries and typically insufficient to directly guide execution.
Search skills when needed: When a specific tool/workflow/methodology is required, the task involves an unfamiliar domain, or a ready-made solution is desired
search_skills:query= user intent in 10–30 words,limit3–5- To install a skill →
install_skill(passfull_nameandtarget_dir)
For complex tasks, search both memory and skills simultaneously.
Client Invocation
python3 skills/ultron-1.0.0/scripts/ultron_client.py '{"action":"<action>", ...}'
Available Actions
| Action | Required Params | Description |
|---|---|---|
search_skills |
query |
Semantic skill search, optional limit |
install_skill |
full_name, target_dir |
Install a skill locally |
upload_skill |
paths |
Upload skills (list of skill directory paths) |
upload_memory |
content |
Upload a memory, optional context, resolution, tags |
search_memory |
query |
Search memories, optional detail_level(l0/l1), limit |
get_memory_details |
memory_ids |
Fetch full text (full) by ID |
ingest |
paths, agent_id |
Pass file/directory paths, LLM auto-extracts memories |
ingest_text |
text |
Pass raw text, LLM extracts memories |
What ships with it
5 files 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.
- 5d ago First seen · 78 lines · 16 tokens per session scan A 4ee8261ea50a
ultron is a skill published in the GitHub repository modelscope/ultron (176 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 1,036 once invoked, about $0.0001 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…