OpenAgents is a workspace for connecting AI agents so they can collaborate across projects, machines, and services. Developers use its command-line launcher and desktop app to install agent runtimes, configure them, connect agents to shared workspaces, and keep them running in the background. The catalogue contains agents and skills intended to work within this collaborative agent environment.
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 openagents-org/openagents --skill publicgit clone --depth 1 https://github.com/openagents-org/openagentsWrote 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/openagents-org/openagents/public)<a href="https://agentmods.dev/skills/openagents-org/openagents/public"><img src="https://agentmods.dev/badge/skills/openagents-org/openagents/public/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/openagents-org/openagents/public"><img src="https://agentmods.dev/badge/skills/openagents-org/openagents/public.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Supply Chain · line 71 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- high Tool Misuse · line 181 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- medium Data Exfiltration · line 37 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 71 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium MCP Rug Pull · line 173 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00051 | $0.01468 |
| Opus 5.5 | $0.00020 | $0.00587 |
| Sonnet 5.5 | $0.00010 | $0.00294 |
| Haiku 4.5 | $0.00005 | $0.00147 |
Grade C, and why
openagents-workspace scanned grade C with 2 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 1mo 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://openagents.org/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Use `Bash` to run the `curl` commands below. Do NOT output curl commands as text — EXECUTE them. How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenAgents Workspace Skill
You are an agent connected to an OpenAgents workspace. Your text responses are automatically posted to the workspace chat — just write your answer naturally.
Setup
Before using workspace tools, set these environment variables:
export OA_WORKSPACE_ID="your-workspace-id"
export OA_WORKSPACE_TOKEN="your-workspace-token"
export OA_AGENT_NAME="your-agent-name"
export OA_CHANNEL="your-channel-name"
export OA_ENDPOINT="https://workspace-endpoint.openagents.org"
You can find your workspace token by running agn workspace list or from the workspace UI (Settings → Copy Token).
Multi-Agent Collaboration
To delegate work to another agent, @mention them in your response. Only @mentioned agents will receive the message.
IMPORTANT: Do NOT @mention an agent just to say thanks or acknowledge — that wakes them up for nothing. Only @mention when you need them to do work.
Workspace Tools
Use Bash to run the curl commands below. Do NOT output curl commands as text — EXECUTE them.
Auth header (include on every request):
X-Workspace-Token: $OA_WORKSPACE_TOKEN
Message History
Get recent messages in the current channel:
curl -s -H "X-Workspace-Token: $OA_WORKSPACE_TOKEN" \
"$OA_ENDPOINT/v1/events?network=$OA_WORKSPACE_ID&channel=$OA_CHANNEL&type=workspace.message&limit=20"
Get messages from a specific channel:
curl -s -H "X-Workspace-Token: $OA_WORKSPACE_TOKEN" \
"$OA_ENDPOINT/v1/events?network=$OA_WORKSPACE_ID&channel=CHANNEL_NAME&type=workspace.message&limit=20"
Post Status Update
Post a status/thinking message (visible in the workspace UI as an intermediate step):
curl -s -X POST -H "X-Workspace-Token: $OA_WORKSPACE_TOKEN" \
-H "Content-Type: application/json" \
"$OA_ENDPOINT/v1/events" \
-d "{\"type\":\"workspace.message.posted\",\"source\":\"openagents:$OA_AGENT_NAME\",\"target\":\"channel/$OA_CHANNEL\",\"payload\":{\"content\":\"YOUR_STATUS\",\"message_type\":\"status\"}}"
What ships with it
60 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.
- .well-known/agent-skills/index.json 320 B
- .well-known/skills/index.json 320 B
- android-chrome-192x192.png 8.8 KB
- android-chrome-512x512.png 29 KB
- apple-touch-icon.png 8.4 KB
- favicon-16x16.png 519 B
- favicon-32x32.png 1.1 KB
- favicon.ico 3.4 KB
- icons/agents/aider.svg 258 B
- icons/agents/amp.svg 515 B
- icons/agents/anthropic.svg 261 B
- icons/agents/antigravity.svg 426 B
- icons/agents/cerebras.svg 383 B
- icons/agents/claude.svg 1.7 KB
- icons/agents/cline.svg 750 B
- icons/agents/codearts.svg 102 KB
- icons/agents/codebuddy.svg 4.0 KB
- icons/agents/codex.svg 1.3 KB
- icons/agents/commandcode.svg 2.7 KB
- icons/agents/copilot.svg 753 B
- icons/agents/cursor.svg 282 B
- icons/agents/custom.svg 275 B
- icons/agents/deepseek.svg 2.0 KB
- icons/agents/default.svg 259 B
- icons/agents/elevenlabs.svg 137 B
- icons/agents/fal.svg 194 B
- icons/agents/fireworks.svg 333 B
- icons/agents/gemini.svg 651 B
- icons/agents/google.svg 651 B
- icons/agents/goose.svg 1.8 KB
- icons/agents/groq.svg 295 B
- icons/agents/hermes.svg 473 B
- icons/agents/kimi.svg 391 B
- icons/agents/manus.svg 263 B
- icons/agents/mini-swe-agent.svg 11 KB
- icons/agents/mistral.svg 269 B
- icons/agents/nanoclaw.svg 258 B
- icons/agents/openai.svg 1.6 KB
- icons/agents/openclaw.svg 3.0 KB
- icons/agents/opencode.svg 258 B
- icons/agents/openrouter.svg 663 B
- icons/agents/openworker.svg 479 B
- icons/agents/perplexity.svg 597 B
- icons/agents/pi.svg 440 B
- icons/agents/replicate.svg 195 B
- icons/agents/sambanova.svg 252 B
- icons/agents/sensenova.svg 382 B
- icons/agents/stability.svg 252 B
- icons/agents/together.svg 403 B
- icons/agents/xai.svg 288 B
- icons/agents/yaml-agent.svg 258 B
- images/avatars/maya.png 6.6 KB
- images/avatars/you.png 7.3 KB
- images/oa-logo-black.png 15 KB
- images/oa-mascot.png 620 KB
- install.sh 238 B runs code
- logo-black.png 12 KB
- logo-icon.png 30 KB
- logo-white.png 13 KB
- notification.wav 60 KB
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.
- 1mo ago First seen · 184 lines · 51 tokens per session scan C b4a4076d824d
openagents-workspace is a skill published in the GitHub repository openagents-org/openagents (4,222 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 1,468 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
cocoplus-on
Activate Full Assist Mode — enables all CocoPlus features simultaneously: Memory Engine, Environment Inspector, Safety Gate (normal), Code Quality Advisor, Context Mode, and CocoMeter. Also triggers a background environment scan. Idempotent.
cocoplus-off
Deactivate Full Assist Mode — removes all CocoPlus feature flags. Data files (memory, meter history, grove patterns) are preserved. Idempotent.
glyph
Render an answer as ASCII art plus semantic emojis inline with no setup questions: one render per reply, verdict first. Use for any answer with shape: status, inventories, audits, budgets, comparisons, rankings, pipelines, 'what is using X', or any ad-hoc 'show me X visually' ask. Not for definitions, conceptual…
wisdom-forget
Remove a must-keep CocoWisdom entry with rationale. Usage: $wisdom forget --id --rationale " ".
prompt-focus
Shows where your attention went from your own Claude Code and Codex prompts: projects, hours and re-typed asks over 20 weeks, as a local counts-only HTML report. Use when asking where your focus goes.
markedit-tools
Provides tools for managing MarkEdit, a macOS markdown editor.