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 cyborg-garden/hermes-agent-mt --skill dream-loopgit clone --depth 1 https://github.com/cyborg-garden/hermes-agent-mtWrote 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/cyborg-garden/hermes-agent-mt/dream-loop)<a href="https://agentmods.dev/skills/cyborg-garden/hermes-agent-mt/dream-loop"><img src="https://agentmods.dev/badge/skills/cyborg-garden/hermes-agent-mt/dream-loop/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/cyborg-garden/hermes-agent-mt/dream-loop"><img src="https://agentmods.dev/badge/skills/cyborg-garden/hermes-agent-mt/dream-loop.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 | $0.00016 | $0.03317 |
| Opus 5.5 | $0.00006 | $0.01327 |
| Sonnet 5.5 | $0.00003 | $0.00663 |
| Haiku 4.5 | $0.00002 | $0.00332 |
Grade A, and why
dream-loop 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 5d 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.
This is a copy
100% identical to dream-loop — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dream Loop Skill
An autonomous process for building extremely impressive visuals, especially 3D scenes (games, apps, usually browser three.js/WebGL): generate photorealistic concept art of the ideal result, build it, screenshot the live build, have a judge score screenshot vs concept against a gated ladder, and iterate until convergence. Goal: the most visually stunning result at an acceptable frame rate for the target platform (e.g. 60 fps browser, 120 fps modern mobile).
This skill does NOT cover general web-app functionality, 2D UI design, or non-visual quality — only the visual-fidelity loop.
When to Use
- User says "dream loop" or asks for a game/scene/app built to a very high level of graphical fidelity.
- Follow-up refinement passes on an existing visual product (see Follow-up loops below).
Prerequisites
- Concept art: the
image_generatetool. If unavailable, stop and ask the user for a concept image (or an image-generation API to connect to). - Screenshots:
browser_exec— serve the build locally (python3 -m http.serverfor static builds), thennew_tab(url),wait_for_load(),capture_screenshot(). - Judging:
vision_analyze(see Judge section for the one-image-per-call workaround). - Optional: Blender for asset modeling — see the
blender-3d-automationskill.delegate_taskfor parallel asset work and fresh-context judging.
If you don't have the tools needed for the full loop, flag that to the user early and stop.
Quick Reference
| Stage | What happens | Artifacts (.dream-loop/) |
|---|---|---|
| 1. Target | Get/confirm the user's description | notes |
| 2. Concept | Generate "in-engine screenshot" concept art | concept.png |
| 3. Budget | Record time budget & start time (if given) | notes |
| 4. Build | Implement the concept as well as possible in one go | source, plans |
| 5. Screenshot | Capture live build at concept resolution | round-N.png |
| 6. Self-check | Rigorous side-by-side audit before judging | assessment log |
| 7. Judge | Ladder-scored comparison, actionable directives | verdict log |
| 8. Iterate/Exit | Address directives or exit per criteria | — |
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.
- 5d ago First seen · 283 lines · 16 tokens per session scan A 188dac5e2989
dream-loop is a skill published in the GitHub repository cyborg-garden/hermes-agent-mt (14 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 3,317 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to dream-loop, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
hermes-memory-providers
Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.
mnemosyne
Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.
mnemosyne-memory-override
Stricter, user-selected override that forces Mnemosyne for all durable memory storage, including small standing rules. Apply it only when the user has consciously chosen this policy; installation, this skill appearing in the skills index, or an ordinary memory task is not that choice. Without it, the default applies…
vrchat-world-queries
VRChat world: new worlds, recommend, lore, X creators.
worker-visualizer
A real-time data/particle/simulation visualizer whose heavy compute runs in a Web Worker (off the main thread), optionally sharing memory with the UI via SharedArrayBuffer, and renders to a canvas at 60fps. Produced as a single self-contained index.html. Use when the brief asks for a "web worker", "simulation"…
sdf
SDFormat/SDF model and world authoring, validation, and simulator handoff. Use for .sdf files, SDFormat XML, models, worlds, links, joints, poses, frames, inertials, visual/collision geometry, mesh URIs, sensors, lights, physics, plugins, includes, Gazebo, static SDF review, or simulator-specific metadata. Do not use…