# Tracking Objects

> Long-running skill that drives the SAM3 tracker from the

- **Type:** Skill
- **Install:** `agentstack add skill-graph-robots-open-robot-skills-tracking-objects`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [graph-robots](https://agentstack.voostack.com/s/graph-robots)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [graph-robots](https://github.com/graph-robots)
- **Source:** https://github.com/graph-robots/open-robot-skills/tree/main/skills/tracking-objects

## Install

```sh
agentstack add skill-graph-robots-open-robot-skills-tracking-objects
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# tracking-objects

Long-running tracker skill. Init on first frame, update per tick, close on
exit. Used as a parallel sibling to other long-running skills (e.g. a
policy) when continuous state estimation is needed.

The skill is **class-based and stateful**: the tracker session id and the
last good mask/box live on the skill instance, so repeated visits to the
same state within one workflow execution can resume the session instead of
re-seeding it (pass `close_on_exit: false` to keep the session open across
visits; the final visit — or the instance teardown — closes it).

It is also a **streaming** skill (`gap.streaming: true`): each update tick
publishes a tracker snapshot
`{mask, box, confidence, object_present, n_updates}` via `ctx.publish`, so
downstream `{"$ref": ""}` consumers see the latest tracked state
while the loop is still running.

## Install

Depends on the **sam3** tool bundle:

```bash
uv sync --extra sam3   # (pip: pip install -e "open-robot-skills[sam3]")
```

## When to use

- A workflow that needs the live mask + box of an object across many
  frames (e.g., a supervisor that monitors a target's location while a
  policy manipulates it).
- Wrapped under a `parallel` state with a `join_policy` so the tracker is
  cooperatively cancelled when the sibling branch finishes (the loop
  checks `ctx.cancel_token` every tick).

## Output

Returns the final mask, box, confidence, and a flag indicating whether
the object was visibly present at exit. Intermediate updates are
published as streaming snapshots; the return value exposes only the
final state.

## Tool form

The bundle also exposes the loop as a flat tool —
`tracking-objects.track` — for callers that want to invoke it as a single
unit (one fresh tracker session per call) rather than as a workflow
state.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [graph-robots](https://github.com/graph-robots)
- **Source:** [graph-robots/open-robot-skills](https://github.com/graph-robots/open-robot-skills)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-graph-robots-open-robot-skills-tracking-objects
- Seller: https://agentstack.voostack.com/s/graph-robots
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.