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 skillgit 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/skill)<a href="https://agentmods.dev/skills/openagents-org/openagents/skill"><img src="https://agentmods.dev/badge/skills/openagents-org/openagents/skill/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/skill"><img src="https://agentmods.dev/badge/skills/openagents-org/openagents/skill.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 | $0.00026 | $0.01372 |
| Opus 5.5 | $0.00010 | $0.00549 |
| Sonnet 5.5 | $0.00005 | $0.00274 |
| Haiku 4.5 | $0.00003 | $0.00137 |
Grade A, and why
add-openagents scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# curl -fsSL https://raw.githubusercontent.com/openagents-org/openagents/develop/packages/agent-connector/nanoclaw-channel/openagents.ts \ How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add OpenAgents Channel
Adds a native NanoClaw channel (channel_type: openagents) that lets an
OpenAgents Workspace talk to one of your Agent Groups. It plumbs into the normal
router/delivery path like the built-in cli channel — no database access,
no host special-casing. The channel owns a local Unix socket at
data/openagents/bridge.sock; the OpenAgents agent-connector (@openagents-org/agent-launcher,
adapter nanoclaw) is the client and does all Workspace IO. No OpenAgents
token is stored in NanoClaw.
Install
Pre-flight (idempotent)
Skip to Wire an Agent Group if all of these are already in place:
src/channels/openagents.tsexistssrc/channels/index.tscontainsimport './openagents.js';
Otherwise continue. Every step below is safe to re-run.
1. Copy the channel module
The channel source ships with the OpenAgents agent-launcher. Copy it from the installed package (preferred), or fetch it from the OpenAgents repo:
# From the installed launcher package (path may vary by install method):
cp "$(node -e "process.stdout.write(require.resolve('@openagents-org/agent-launcher/nanoclaw-channel/openagents.ts'))" 2>/dev/null \
|| echo "$HOME/.openagents/runtimes/nanoclaw/node_modules/@openagents-org/agent-launcher/nanoclaw-channel/openagents.ts")" \
src/channels/openagents.ts
# …or fetch from source:
# curl -fsSL https://raw.githubusercontent.com/openagents-org/openagents/develop/packages/agent-connector/nanoclaw-channel/openagents.ts \
# -o src/channels/openagents.ts
The OpenAgents Launcher can also install this for you automatically — it calls the same copy + barrel-patch. This skill is the manual / auditable path.
2. Append the self-registration import
Append to src/channels/index.ts (skip if already present):
// openagents channel (OpenAgents Workspace bridge)
import './openagents.js';
3. Restart the NanoClaw host
The channel self-registers on startup. Restart the host (./nanoclaw.sh restart,
or your launchd/systemd unit) so it loads. After restart you should see
openagents channel listening in the logs and a data/openagents/bridge.sock 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.
- 1mo ago First seen · 120 lines · 26 tokens per session scan A 224e133b20d2
add-openagents is a skill published in the GitHub repository openagents-org/openagents (4,222 stars, last pushed today), licensed Apache-2.0. It adds 26 tokens to every session and 1,372 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (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
ai-agent-evaluation-benchmarking
Autonomous AI agent benchmark evaluation register: task completion rates, planning accuracy, tool invocation precision, and cost benchmarks.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
feature-design
Choose the design, record the alternatives and CUJ coverage, or stop when a choice needs a human.
security-audit
Audit a codebase or directory for security issues (hardcoded secrets, injection, unsafe deserialization, weak crypto, authz gaps) and produce a structured findings report. Use when the user asks for a security review, an audit, or to check code for vulnerabilities. Report only — never fix.