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 agentmods add instructions/oculus-samples/voicesdk-samples-whisperer/agents-mdgit clone --depth 1 https://github.com/oculus-samples/voicesdk-samples-whispererWrote 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/instructions/oculus-samples/voicesdk-samples-whisperer/agents-md)<a href="https://agentmods.dev/instructions/oculus-samples/voicesdk-samples-whisperer/agents-md"><img src="https://agentmods.dev/badge/instructions/oculus-samples/voicesdk-samples-whisperer/agents-md.svg" alt="Measured on agentmods" 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 | $0.00795 | $0.00795 |
| Opus 5 | $0.00398 | $0.00398 |
| Sonnet 5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
voicesdk-samples-whisperer AGENTS.md 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 6d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions — Whisperer (Voice SDK Sample)
Unity VR sample game showcasing the Meta Voice SDK (powered by Wit.ai) for natural-language interaction. Players raise their hands as if speaking through them and direct objects in the world with voice commands.
Source-of-truth files (read these first, do not duplicate their contents in this file)
For setup, build steps, SDK versions, and project layout, read:
README.md— official setup, Wit.ai configuration, and intent/entity referenceProjectSettings/ProjectVersion.txt— Unity editor versionPackages/manifest.json— Unity package versions (Meta Voice SDK, Interaction SDK, XRI, URP)Assets/Whisperer/Scripts/Voice/— voice plumbing (SpeakGestureWatcher.cs,Listenable.csand subclasses)Assets/Whisperer/Scripts/Logic/—LevelLoader.cs,LevelManager.cs, per-level managersLICENSE— license terms (MIT only forAssets/Whisperer/; Oculus License otherwise)
Quest / Horizon-specific notes
- Git LFS is required. Run
git lfs installbefore cloning. - A configured Wit.ai app is mandatory. Without it the mic activates but nothing parses — diagnose Wit setup before chasing voice logic bugs.
- Wit.ai trains asynchronously after importing
Assets/whisperer-wit-app.zip; the green dot in the Wit dashboard means the model is ready. Calling voice APIs before training finishes returns empty or wrong responses. - If the README and
Packages/manifest.jsondisagree on Voice SDK version, trust the manifest. - Voice intents use the Voice SDK Conduit framework via the
[MatchIntent("...")]attribute; renaming or removing those handlers will silently break voice commands.
Meta Quest tooling
This is a Meta Quest / Horizon OS sample. The bespoke intro above is the source of truth for what this project is and how it's built — use it (and the files it points at) instead of restating facts from memory.
When the user asks anything about Quest device behavior, build / deploy / debug / capture flows, on-device performance, or Horizon OS APIs, reach for these tools instead of generic Unity answers:
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.
- 6d ago First seen · 39 lines · 795 tokens per session scan A a7e1c0d3fbd6
voicesdk-samples-whisperer AGENTS.md is an instructions file published in the GitHub repository oculus-samples/voicesdk-samples-whisperer (82 stars, last pushed 3mo ago), licensed MIT. It adds 795 tokens to every session, about $0.0040 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 instructions, from other repositories
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
nes-php-glfw copilot-instructions.md
Instructions for oliverearl/nes-php-glfw, covering github copilot development guidelines for nes emulator, agent document source of truth, project overview, code style & standards and documentation.
game-and-watch-retro-go-sd CLAUDE.md
Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.
base-building-trap-defense-design-agent-skill CLAUDE.md
Instructions for dungnotnull/base-building-trap-defense-design-agent-skill, covering claude.md — skill 250: base-building-trap-defense-design, skill identity, problem this skill solves, harness flow summary and sub-skills.
trident-mcp AGENTS.md
Instructions for mordor-forge/trident-mcp, covering agents.md, what this is, build and test, single-file verification and e2e tests.
unreal-mcp-additional-tools CLAUDE.md
Claude Code instructions for nodormu/unreal-mcp-additional-tools, covering claude.md, what this is, commands, architecture and transports (src/transports/).