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 skills add CoWork-OS/CoWork-OS --skill cowork-multi-agent-researchgit clone --depth 1 https://github.com/CoWork-OS/CoWork-OSWrote 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/cowork-os/cowork-os/cowork-multi-agent-research)<a href="https://agentmods.dev/skills/cowork-os/cowork-os/cowork-multi-agent-research"><img src="https://agentmods.dev/badge/skills/cowork-os/cowork-os/cowork-multi-agent-research/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cowork-os/cowork-os/cowork-multi-agent-research"><img src="https://agentmods.dev/badge/skills/cowork-os/cowork-os/cowork-multi-agent-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00078 | $0.00661 |
| Opus 5 | $0.00039 | $0.00331 |
| Sonnet 5 | $0.00016 | $0.00132 |
| Haiku 4.5 | $0.00008 | $0.00066 |
Grade A, and why
cowork-multi-agent-research 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 13d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CoWork OS Multi-Agent System Research Agent
You are the CoWork OS Multi-Agent System research agent. Follow these instructions to conduct systematic research on multi-agent systems and produce actionable findings for CoWork OS.
Core Workflow
- Read PROGRESS.md first — Always read
PROGRESS.mdbefore any research. Never re-research a topic already marked done. - Pick next topic — Use the next item from the queue, or a newly discovered relevant topic if the queue is empty.
- Search — Find latest multi-agent system papers, frameworks, and production case studies (web search, arXiv, GitHub, blogs).
- Create research document — Write findings, CoWork OS applicability analysis, and implementation recommendations.
- Save — Write to
research/YYYY-MM-DD-topic-slug.md. - Update PROGRESS.md — Record the completed topic and add any new topics to the queue.
File Locations
| File | Purpose |
|---|---|
PROGRESS.md |
Research queue, completed topics, next priorities |
research/YYYY-MM-DD-topic-slug.md |
Individual research documents |
Default paths are relative to the workspace root (project root or ~/.cowork/workspace). If PROGRESS.md does not exist, create it with the template from references/full-guidance.md.
Routing
- Use when: User asks to research multi-agent systems, agent orchestration, multi-agent papers/frameworks, or to continue/run the multi-agent research workflow.
- Do not use when: General coding tasks, unrelated research, or one-off questions that don't fit the research workflow.
- Outputs: Research document saved to
research/, PROGRESS.md updated, summary of findings and next topics.
Research Document Structure
Each research document must include:
- Findings — Summary of papers, frameworks, or case studies with citations.
- CoWork OS applicability — How findings apply to CoWork OS (agent teams, sub-agents, collaborative mode, mention tools, etc.).
- Implementation recommendations — Concrete, actionable steps for CoWork OS.
What ships with it
1 file 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.
- 13d ago First seen · 53 lines · 78 tokens per session scan A 1f1f953c44aa
cowork-multi-agent-research is a skill published in the GitHub repository CoWork-OS/CoWork-OS (452 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 661 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
time-library
Use when the user refers to previous decisions, corrections, forgotten context, already-built work, install/test/release status, source-backed evidence, or next steps in ongoing work. Treat Time Library as a standing active memory routing rule: call timelibraryrecall before answering memory-dependent prompts. Also…
motion-frames
A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
ligandmpnn
Inverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023, github.com/dauparas/LigandMPNN). Reach for this skill to redesign the residues lining a binding pocket around a bound small molecule or cofactor, to design metal-coordinating sites where the geometry must be…
apify-skill
Run web scrapers and extract data from websites and social media platforms using Apify actors. Supports Instagram, TikTok, Twitter/X, LinkedIn, Facebook, YouTube, Google Search, and general web crawling.
browser-skill
Interactive browser automation - navigate, click, type, fill forms, take screenshots, get accessibility snapshots. Supports system Chrome/Edge via auto-detection.