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/publu/roborun/openclawnpx skills add publu/RoboRun --skill openclawgit clone --depth 1 https://github.com/publu/RoboRunWhat 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 | $0.00052 | $0.00730 |
| Opus 5 | $0.00026 | $0.00365 |
| Sonnet 5 | $0.00010 | $0.00146 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade B, and why
roborun scanned grade B 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 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s -X POST $ROBORUN_URL/api/behaviors/enable -H 'Content-Type: application/json' -d '{"name":"sentry"}' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s $ROBORUN_URL/api/health How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RoboRun robot control
The robot runs a RoboRun server on the local network. Talk to it over HTTP. Start every session by setting the base URL (honors an operator override):
ROBORUN_URL="${ROBORUN_URL:-http://127.0.0.1:8765}"
The robot also pushes notifications to you via the gateway's webhook
(/hooks/agent) — messages prefixed "RoboRun notification" arrived that way.
When relaying them, keep it to one short message.
Is it up?
curl -s $ROBORUN_URL/api/health
Behaviors (patrol, sentry, follow_person, ...)
List, with running state:
curl -s $ROBORUN_URL/api/behaviors
Start or stop one ("start the patrol" → enable sentry if present, else patrol):
curl -s -X POST $ROBORUN_URL/api/behaviors/enable -H 'Content-Type: application/json' -d '{"name":"sentry"}'
curl -s -X POST $ROBORUN_URL/api/behaviors/disable -H 'Content-Type: application/json' -d '{"name":"sentry"}'
What does the robot see / what happened?
Live detections and pose:
curl -s $ROBORUN_URL/api/state
Recent timeline events (detections, behavior logs, notifications):
curl -s "$ROBORUN_URL/api/run/events"
Camera snapshot metadata: curl -s $ROBORUN_URL/api/camera
Onboard a new robot ("set up roborun on 192.168.1.42")
RoboRun is a CLI — you can do the whole setup from this chat:
pip install ros-agent # if `roborun` isn't on PATH yet
roborun connect 192.168.1.42 # finds rosbridge, classifies the robot, remembers it
roborun connect 192.168.1.42 --move # proves control: clamped 0.5s nudge, then stop
If rosbridge isn't running on the robot, connect prints the exact two
lines to run there — relay them to the user. Ask before --move: it
physically moves the robot. Then start the server with roborun (it
serves the dashboard, MCP, and this HTTP API).
Install behaviors/skills from GitHub
roborun skill add someuser/their-skill # validated without executing, pinned to the commit SHA
roborun skill list # installed skills + pin state
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 · 87 lines · 52 tokens per session scan B 3a6b1b45ee43
roborun is a skill published in the GitHub repository publu/RoboRun (12 stars, last pushed 6d ago), licensed MIT. It adds 52 tokens to every session and 730 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, 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
bring-photo-mcp
Turn product photos into verified Bring! list items via MCP.
score-studio
Use Score Studio to inspect versioned computer-vision data and models, start training or evaluation, review evidence, verify deployments, and run workflows. Trigger for Score Studio datasets, CV training, evaluation gates, model release evidence, deployments, or visual workflows.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
client-scripts
Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.
agoragentic-transaction-assurance
Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…
linkding
Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.