Orchestrate coding agents with review loops, parallel races, repeat passes, and task-list progression. Use when: the user asks to "cook" something, wants iterative refinement, wants to race multiple approaches, or needs to work through a task list.
agents
AGENTS
ANo problem foundjaynye/crowd-control
crowd-control builds stochastic, reactive human crowds for training a LiDAR-conditioned humanoid traversal policy, targeting 4,096 parallel mjlab environments with 4–16 humans each. The 2026-09-30 benchmark showed the generative motion backends (ARDY, Kimodo) cannot run online at that scale, so they generate motion offline. The library is stitched online through a stochastic motion graph (or motion matching), or baked per episode if the policy is trained by imitation instead of RL.
AGENTS got grade A on our automated scan on 2026-10-24.
Details
Source
Public file: https://github.com/jaynye/crowd-control/blob/b4542dd8ae1b6530414d6d03112b3021e14b7cc2/AGENTS.md
Last scanned: (Oct 24, 2026, 2:01 a.m. ET)
Category: uncategorized
License: None found
Before you install
- Read any scripts this skill ships.
- Note every URL it fetches.
- Check allowed-tools and hooks.
Embed this grade
Add this badge to your README. It shows the current grade from CheckSkills.
Report this skill if the grade looks wrong, or if something slipped through.
Related
Get the number of lines of code for specific languages while excluding certain directories.
Make AI coding-agent messages to humans clear and easy to follow. Use for every user-facing message in this repository, or when the user asks to simplify or rewrite an agent message.
@agents/skills/AGENTS.md
Review the branch with /code-review at high, then answer the findings with /code-review-response.