Borrowing it
Nothing to install: this file belongs to AssemblyAI/blurt. 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/AssemblyAI/blurt/main/AGENTS.mdgit clone --depth 1 https://github.com/AssemblyAI/blurtWrote 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/assemblyai/blurt/agents-md)<a href="https://agentmods.dev/instructions/assemblyai/blurt/agents-md"><img src="https://agentmods.dev/badge/instructions/assemblyai/blurt/agents-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/assemblyai/blurt/agents-md"><img src="https://agentmods.dev/badge/instructions/assemblyai/blurt/agents-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 | $0.30049 | $0.30049 |
| Opus 5.5 | $0.12020 | $0.12020 |
| Sonnet 5.5 | $0.06010 | $0.06010 |
| Haiku 4.5 | $0.03005 | $0.03005 |
Grade A, and why
blurt 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 today.
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 — 1,433 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
The canonical agent guide for this repository. CLAUDE.md is a shim that points here; it also maps
the Claude-Code-specific tooling under .claude/ (hooks, skills, subagents).
Start here
Blurt is a macOS dictation app powered by AssemblyAI. Tap or hold a
trigger key, speak, and polished text is pasted into the focused app. Transcription is one remote
AssemblyAI dictation API call: the audio plus a request for the service's server-side LLM cleanup
rewrite (config.llm_instruction), so the text that comes back is already polished. (A recording
past the streaming route's 120 s cap is the one exception: it is sent again, whole, to the
buffered route — see the over-cap fallback.) The user supplies their own
API key. The request's stt_prompt carries two context signals, newline-joined oldest first: the
user's recent dictations, then the text immediately before the cursor. The frontmost app, the
window title, the focused field's label, and the selected text are captured for local work (paste
spacing, the injector's window identity, the developer-mode log) and none of them go on the wire.
stt_prompt and prompt are the same field, so never send both. The user's key terms ride a second
field, keyterms_prompt, as a flat list of strings. See
Contextual prompt and key terms.
Four reflexes before you touch anything:
scripts/check.shis the definition of green — the same script CI runs. Off-Mac, onlyscripts/check.sh --portableis available and it is not green in the CI sense. See Verifying your work.- Read Settled decisions before changing architecture. Every entry was tried the other way and reverted; reintroducing one is the most likely way to make things worse.
- Never hand-edit
App/Blurt/Blurt.xcodeproj/project.pbxproj— it is generated fromApp/Blurt/project.yml. Edit the yml, runxcodegen generateon a Mac, commit the result. - No external SPM dependencies in the engine (rule, guarded by
check.sh); the app carries the localBlurtEnginepackage plus exactly one remote package, Sparkle (the updater), andcheck.shrejects any other.
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.
- today Changed · +58 lines · +1,403 tokens per session f29f0cfbafda
- 7d ago Changed · +39 lines · +974 tokens per session dc1152d30858
- 14d ago Changed · +25 lines · +548 tokens per session aa45876b3d94
- 27d ago Changed · +64 lines · +2,188 tokens per session 60f2dc04e306
- 28d ago Changed · +45 tokens per session 0ce75ef72dae
- 1mo ago Changed · -7 lines · -35 tokens per session b7f4baa6ae9b
- 1mo ago Changed · +10 lines · +206 tokens per session be1d57e5d9f0
- 1mo ago Changed · +5 lines · +99 tokens per session fcb82072c06c
- 1mo ago Changed · +3 lines · +57 tokens per session 0b48721cddd3
- 1mo ago First seen · 1,236 lines · 24,564 tokens per session scan A 889eeb97000c
blurt AGENTS.md is an instructions file published in the GitHub repository AssemblyAI/blurt (65 stars, last pushed today), licensed MIT. It adds 30,049 tokens to every session, about $0.1202 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.