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 SummerEngine/summer-engine-agent --skill ambient-bedgit clone --depth 1 https://github.com/SummerEngine/summer-engine-agentWrote 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/summerengine/summer-engine-agent/ambient-bed)<a href="https://agentmods.dev/skills/summerengine/summer-engine-agent/ambient-bed"><img src="https://agentmods.dev/badge/skills/summerengine/summer-engine-agent/ambient-bed/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/summerengine/summer-engine-agent/ambient-bed"><img src="https://agentmods.dev/badge/skills/summerengine/summer-engine-agent/ambient-bed.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 | $0.00089 | $0.03241 |
| Opus 5.5 | $0.00036 | $0.01296 |
| Sonnet 5.5 | $0.00018 | $0.00648 |
| Haiku 4.5 | $0.00009 | $0.00324 |
Grade A, and why
ambient-bed 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 1mo 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ambient-bed — Long Looping Location Ambience
Overview
An ambient bed is the air of a place. Forest at dawn, dungeon corridor, spaceship hum, market street, ocean cave. It plays at low energy under everything else — never melodic, never drawing attention, but its absence is immediately felt. Players don't notice an ambient bed; they notice the silence when you forget one.
This is not music. Use summer_generate_audio({capability: 'sound_effects'}), not {capability: 'music'}. SFX renders textures; Music renders melody. You want texture.
Generated at 15–22 seconds (the SFX duration ceiling) and looped with a Summer Engine import loop point and optional crossfade.
When to use
- Location bed for a level, room, biome, or zone.
- Background hum / drone under dialogue scenes.
- Atmosphere layer that complements a music track.
When NOT to use
- Short event SFX (<5s) →
audio/sound-effect. - Music with melody / chord progression →
audio/music-track. - Voice barks →
audio/voice-line.
Steps
1. Read the audio bible
Read .summer/audio-bible.md
The bible's Ambient layer SFX class names the character — usually "continuous, low presence, no looping melody". Honor it. The mix rules sit ambient at the bus level the bible defined (typically Ambient bus around -12 dB).
2. Identify the location
Ask if it's not pinned by context:
Which location's ambience? Be specific — "forest at dawn with light wind and distant birds" beats "outdoors". The model needs the time of day, the weather, and 2–3 sound sources.
3. Build the prompt — environment + time + weather + 2–3 sources + density + duration
ElevenLabs SFX renders ambient textures well when the prompt names sources, not vibes.
Prompts that work:
forest at dawn, gentle wind through leaves, distant bird calls every 6 seconds,
soft creaking branches, no music, no human sound, 22s seamless loop
stone dungeon corridor, distant water drip, low rumble, faint draft, no music,
no creature sound, 22s seamless loop
spaceship corridor, low hum at 60Hz, occasional electronic chirp, ventilation
whoosh, no human voices, 22s seamless loop
medieval marketplace at noon, distant chatter, footsteps on stone, occasional
horse, distant blacksmith hammer, no recognisable words, 22s loop
ocean cave, slow waves entering, low rumble, water drip echoes, no seagulls,
22s seamless loop
night swamp, crickets, distant owl, slow water lapping, occasional frog,
22s seamless loop
abandoned office building, fluorescent hum, distant air conditioning, faint
paper rustle from a vent, no human sound, 22s loop
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.
- 1mo ago First seen · 285 lines · 89 tokens per session scan A 7cd84d0b9ad1
ambient-bed is a skill published in the GitHub repository SummerEngine/summer-engine-agent (59 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 3,241 once invoked, about $0.0004 per session on Opus 5.5. 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
self-evolve
Capture reusable patterns from a finished project and lift them into framework-level priors (contracts, modules, skeletons) that future projects inherit. Run only when the user explicitly requests self-evolution; the orchestrator executes the workflow.
artist-self-evolve
Distill stable art-generation patterns from a completed project, so future projects produce comparable assets without re-discovering the prompts. Lead-dispatched only — orchestrator invokes this skill from its self-evolve flow with a game-slug message; do not self-trigger.
vibegame-build
Run VibeGame's standard end-to-end game development workflow with reviewer gates. Use when the user wants to create a game from zero or evolve an existing game across multiple stages.
vibegame-start
Resume a VibeGame orchestrator session after vibegame start. Use at the beginning of a Claude or Codex session to inspect team runtime state, repair missing persistent members, load goal and GDD context, inspect tasks, and ask the user what to do next.
vibegame-edit
Iterate broadly on an existing game, on top of vibegame-build. Use when the user asks to change an existing game's art style, genre, or core rules. Not for local tuning such as numbers or game feel. Orchestrator only.
hearth-feel
Make a Hearth game feel good, not just run — the juice stack (hit-stop, screen shake, flash, particle bursts, layered sound), tween easing, camera effects, anticipation/recovery animation idioms, game-UX conventions (menus, pause, onboarding, difficulty, save etiquette), effect-asserting playtests, and the quality bar…