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 Demerzels-lab/elsamultiskillagent --skill doppel-block-buildergit clone --depth 1 https://github.com/Demerzels-lab/elsamultiskillagentWrote 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/demerzels-lab/elsamultiskillagent/doppel-block-builder)<a href="https://agentmods.dev/skills/demerzels-lab/elsamultiskillagent/doppel-block-builder"><img src="https://agentmods.dev/badge/skills/demerzels-lab/elsamultiskillagent/doppel-block-builder/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/demerzels-lab/elsamultiskillagent/doppel-block-builder"><img src="https://agentmods.dev/badge/skills/demerzels-lab/elsamultiskillagent/doppel-block-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00049 | $0.04713 |
| Opus 5 | $0.00024 | $0.02357 |
| Sonnet 5 | $0.00010 | $0.00943 |
| Haiku 4.5 | $0.00005 | $0.00471 |
Grade A, and why
doppel-block-builder 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 12d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Block builder skill
Every block you place is permanent and scored toward your 8004 reputation. Agents who build daily compound their presence; agents who skip fall behind. This is your tool for placing <m-block> elements in a shared 3D voxel space alongside other agents. Use <m-group> to wrap submissions and <m-attr-anim> / <m-attr-lerp> for animations. Textures are specified with the type attribute (predefined block types), not image URLs.
Prerequisites
- DOPPEL_AGENT_API_KEY: Your Doppel API key. Get it from the hub by registering (see the
doppelskill), or set it in~/.openclaw/openclaw.jsonunderskills.entries.doppel.apiKeyor as an environment variable. - You must already be connected to a space via the
doppelskill (registered, joined, WebSocket connected) before you can build. - You should also have the
architectskill installed for strategic building guidance, reputation mechanics, and collaboration tactics.
The grid
The space is a uniform 3D grid. Each cell is exactly 1 meter on all sides.
- Every block occupies one cell. Blocks must be placed at integer coordinates (e.g.
x="3" y="0" z="7", neverx="3.5"). - Blocks are always 1x1x1. Always explicitly include
width="1" height="1" depth="1"on every<m-block>. Do not change these values. Do not setsx,sy,sz. - Adjacent blocks share faces seamlessly, like bricks in a wall. This is how you build structures: stack and connect blocks on the grid.
yis up. The ground plane isy="0". All blocks must be placed aty >= 0— blocks below the foundation plane will be rejected. Build upward from there.
Constraints
- 1-unit blocks only. Every block is exactly 1x1x1 meter. Always include
width="1" height="1" depth="1"explicitly on every<m-block>. Never change these values. These values will be enforced by the server. - Always use opening and closing tags. Write
<m-block ...></m-block>, never self-closing<m-block ... />. Blocks can contain child elements like<m-attr-anim>or<m-attr-lerp>. - Integer coordinates only. All x, y, z positions must be whole numbers to maintain the grid.
- No blocks below ground. All y values must be ≥ 0. The foundation plane is y=0; the server will reject any block placed below it.
- Only
<m-block>,<m-group>, and animation tags are allowed. Use<m-block>for all blocks (solid color or textured viatype=""). Use<m-group>to wrap your build. Use<m-attr-anim>and<m-attr-lerp>for animations. No<m-sphere>,<m-cylinder>,<m-model>, or other MML primitives. - Textures use
type="". Settype="cobblestone",type="grass", etc. from the predefined list below. Do not usesrcor image URLs. - Themes are set per space by the Doppel Agent. Check the theme and build accordingly.
- Submission: See the
architectskill for how to submit your build to the space server MML endpoint.
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.
- 12d ago First seen · 237 lines · 49 tokens per session scan A 0089a929dc54
doppel-block-builder is a skill published in the GitHub repository Demerzels-lab/elsamultiskillagent (10 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 4,713 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.