Borrowing it
Nothing to install: this file belongs to sapoepsilon/Whispera. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sapoepsilon/Whispera/main/CLAUDE.mdgit clone --depth 1 https://github.com/sapoepsilon/WhisperaWrote 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/sapoepsilon/whispera/claude-md)<a href="https://agentmods.dev/instructions/sapoepsilon/whispera/claude-md"><img src="https://agentmods.dev/badge/instructions/sapoepsilon/whispera/claude-md/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/instructions/sapoepsilon/whispera/claude-md"><img src="https://agentmods.dev/badge/instructions/sapoepsilon/whispera/claude-md.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 | $0.03394 | $0.03394 |
| Opus 5.5 | $0.01358 | $0.01358 |
| Sonnet 5.5 | $0.00679 | $0.00679 |
| Haiku 4.5 | $0.00339 | $0.00339 |
Grade A, and why
Whispera CLAUDE.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 2d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Whispera is a native macOS app (macOS 14+, Apple Silicon) that replaces built-in dictation with on-device speech recognition. Whisper models run through WhisperKit and NVIDIA Parakeet models through FluidAudio. It covers dictation into any text field, live transcription, file/URL/YouTube transcription, optional LLM post-processing, transcription history, and automation through a CLI, whispera:// links, App Intents and Raycast.
Build & Development Commands
Requires Xcode 26: OTHER_LDFLAGS weak-links FoundationModels (Apple Intelligence post-processing), which only the macOS 26 SDK provides.
Building
xcodebuild -scheme Whispera -project Whispera.xcodeproj build
Testing
# Unit tests (what CI runs on pull requests; model-dependent tests skip themselves)
xcodebuild test -scheme Whispera -project Whispera.xcodeproj -only-testing:WhisperaUnitTests
# On a machine with openai_whisper-small downloaded by the app: model tests must run, and a
# missing model fails them instead of skipping (use this before merging live-mode changes)
TEST_RUNNER_WHISPERA_REQUIRE_MODEL_TESTS=1 xcodebuild test -scheme Whispera -project Whispera.xcodeproj \
-only-testing:WhisperaUnitTests -parallel-testing-enabled NO
# UI tests
xcodebuild test -scheme Whispera -project Whispera.xcodeproj -only-testing:WhisperaUITests
The WhisperaUnitTests target compiles the Swift Testing suites in WhisperaUnitTests/ plus five of the XCTest files in WhisperaTests/ (AppLibraryManagerTests, AudioDeviceManagerTests, LargeModelTranscriptionTests, SingleInstanceTests, VersionTests); there is no separate WhisperaTests target. The other files in WhisperaTests/ (AudioManagerTests, FileDropHandlerIntegrationTests, ModelSynchronizationTests, PermissionManagerTests, SimpleTest, StreamingTranscriptionIntegrationTests, WhisperKitTranscriberTests) are not in any target's Sources phase and do not build.
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.
- 2d ago Changed 93cc0c330266
- 1mo ago Changed · +43 lines · +1,820 tokens per session 86a9646a244a
- 2mo ago First seen · 167 lines · 1,574 tokens per session scan A 4a01bfde6542
Whispera CLAUDE.md is an instructions file published in the GitHub repository sapoepsilon/Whispera (168 stars, last pushed today), licensed MIT. It adds 3,394 tokens to every session, about $0.0136 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.
Whispera CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Whispera CLAUDE.mdsapoepsilon/Whispera | Instructions file | 168 | today | MIT | A | 3,394 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |