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/danmartinez78/vectorclaw/skillnpx skills add danmartinez78/VectorClaw --skill skillgit clone --depth 1 https://github.com/danmartinez78/VectorClawWhat 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 | $0.00026 | $0.00710 |
| Opus 5 | $0.00013 | $0.00355 |
| Sonnet 5 | $0.00005 | $0.00142 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
vectorclaw-mcp 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 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.
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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VectorClaw MCP
VectorClaw connects OpenClaw to an Anki / Digital Dream Labs Vector robot through MCP. It provides practical robot control primitives for speech, movement, camera capture, and status/sensor reads.
What you can do
- Speak text with
vector_say - Move and position with
vector_drive,vector_head,vector_lift - Capture camera images with
vector_lookandvector_capture_image - Read robot state with
vector_status,vector_pose,vector_proximity_status,vector_touch_status - Build look → reason → act workflows
Vision requirement for look → reason → act
For see → reason → act workflows, the agent must either be vision-capable itself (e.g., a VLM) or have access to a separate vision model/image-interpretation tool to analyze camera images before choosing actions.
Requirements
- Vector robot configured and reachable
- Wire-Pod running
- SDK configured at
~/.anki_vector/sdk_config.ini VECTOR_SERIALenvironment variable set
Quick setup
- Install package:
pip install vectorclaw-mcp - Configure SDK:
python3 -m anki_vector.configure - Export robot serial:
export VECTOR_SERIAL=your-serial - Add MCP server:
{
"mcpServers": {
"vectorclaw": {
"command": "python3",
"args": ["-m", "vectorclaw_mcp.server"],
"env": { "VECTOR_SERIAL": "${VECTOR_SERIAL}" }
}
}
}
Tool coverage
Hardware-verified core tools
vector_say, vector_drive_off_charger, vector_drive, vector_emergency_stop, vector_head, vector_lift, vector_look, vector_capture_image, vector_face, vector_scan, vector_vision_reset, vector_pose, vector_status, vector_charger_status, vector_touch_status, vector_proximity_status
Experimental tools
vector_animate, vector_drive_on_charger, vector_find_faces, vector_list_visible_faces, vector_face_detection, vector_list_visible_objects, vector_cube
Current limitations
- Charger return (
vector_drive_on_charger) is currently unreliable - Face/object detection is currently inconsistent
- Visual interpretation requires the vision capability described above
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.
- 2d ago First seen · 88 lines · 26 tokens per session scan A 76fedd5a32ca
vectorclaw-mcp is a skill published in the GitHub repository danmartinez78/VectorClaw (20 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 710 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…