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 HorizonRobotics/EmbodiedGen --skill affordance-deploymentgit clone --depth 1 https://github.com/HorizonRobotics/EmbodiedGenWrote 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/horizonrobotics/embodiedgen/affordance-deployment)<a href="https://agentmods.dev/skills/horizonrobotics/embodiedgen/affordance-deployment"><img src="https://agentmods.dev/badge/skills/horizonrobotics/embodiedgen/affordance-deployment/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/horizonrobotics/embodiedgen/affordance-deployment"><img src="https://agentmods.dev/badge/skills/horizonrobotics/embodiedgen/affordance-deployment.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 | $0.00056 | $0.00599 |
| Opus 5 | $0.00028 | $0.00300 |
| Sonnet 5 | $0.00011 | $0.00120 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
affordance-deployment scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Affordance Deployment
Use the repository installer first. It initializes both submodules, builds
torch-scatter, flash-attn==2.8.2, and GraspGen's pointnet2_ops, then
restores the supported OpenCV versions.
bash install.sh affordance
affordance-cli --help
img3d-cli --help
CUDA Architecture
Load the CUDA hook before rebuilding extensions and verify the selected target:
echo "$CUDA_HOME"
echo "$TORCH_CUDA_ARCH_LIST"
nvcc --version
- RTX 4090:
TORCH_CUDA_ARCH_LIST=8.9. - RTX 5090:
TORCH_CUDA_ARCH_LIST=12.0and nvcc 12.8 or newer.
If pointnet2_ops was built for the wrong architecture, rebuild the package
directly instead of running thirdparty/GraspGen/install_pointnet.sh, which
hardcodes an older target:
python -m pip install --no-build-isolation --force-reinstall --no-deps \
thirdparty/GraspGen/pointnet2_ops
Flash Attention
Keep flash-attn at 2.8.2 because the installed diffusers version rejects
newer releases. Rebuild from source with the GPU-specific target when needed:
export FLASH_ATTENTION_FORCE_BUILD=TRUE
export FLASH_ATTN_CUDA_ARCHS=89 # use 120 on RTX 5090 with nvcc >= 12.8
python -m pip install --no-cache-dir --no-build-isolation \
--no-binary flash-attn --force-reinstall --no-deps flash-attn==2.8.2
If the source checkout lacks CUTLASS or composable-kernel files, initialize its
submodules before retrying. Reduce MAX_JOBS when compilation runs out of RAM.
Quick Reference
| Error | Root Cause | Fix |
|---|---|---|
Unsupported gpu architecture 'compute_120' |
nvcc is older than 12.8 | Use the cu128 hook or target the actual GPU |
no kernel image in pointnet2 |
Extension built for another GPU | Rebuild pointnet2_ops directly |
| diffusers rejects flash-attn | Version is newer than 2.8.2 | Reinstall 2.8.2 |
| Build OOM | Too many compiler jobs | Set MAX_JOBS=4 |
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.
- 10d ago First seen · 63 lines · 56 tokens per session scan A a5109ce58917
affordance-deployment is a skill published in the GitHub repository HorizonRobotics/EmbodiedGen (660 stars, last pushed 16d ago), licensed Apache-2.0. It adds 56 tokens to every session and 599 once invoked, about $0.0003 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…