blurt AGENTS.md

A repository guide for coding agents working on Blurt, a macOS dictation app that turns speech into polished text. It explains the project structure, its two instruction layers, and how to check your work.

In plain words
What is it for?
Use it when modifying Blurt, especially its agent instructions, AssemblyAI transcription flow, context handling, macOS integrations, or verification steps.
Why use it?
It gives an agent the project-specific rules and background needed before changing code. This reduces guesswork about how dictation, context, privacy, and verification work.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/assemblyai/blurt/agents-md
Clone the repo
git clone --depth 1 https://github.com/AssemblyAI/blurt

Made for: Codex, OpenCode.

Per session 22,629 This file is loaded in full into every session.
When invoked 22,629 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.22629 $0.22629
Opus 5 $0.11314 $0.11314
Sonnet 5 $0.04526 $0.04526
Haiku 4.5 $0.02263 $0.02263

Measured 2d ago against content hash cf9c5b6e9e95, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

AGENTS.md · 1,172 lines

How it starts

The opening of the file, as written. The whole thing — 1,172 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), so the text that comes back is already polished. The user supplies their own API key. The request's conversation_context carries two context signals, as ordered turns: 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. There is no config.prompt — the context field replaced it. The user's key terms ride a second field, word_boost, as a flat list of strings. See Conversation context and key terms.

Four reflexes before you touch anything:

  1. scripts/check.sh is the definition of green — the same script CI runs. Off-Mac, only scripts/check.sh --portable is available and it is not green in the CI sense. See Verifying your work.
  2. 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.
  3. Never hand-edit App/Blurt/Blurt.xcodeproj/project.pbxproj — it is generated from App/Blurt/project.yml. Edit the yml, run xcodegen generate on a Mac, commit the result.
  4. No external SPM dependencies in the engine (rule, guarded by check.sh); the app carries only the local BlurtEngine package.

Read the full file on GitHub · 1,172 lines

Changes

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.

  1. 2d ago First seen · 1,172 lines · 22,629 tokens per session scan A cf9c5b6e9e95

Subscribe to this mod's changes

blurt AGENTS.md is an instructions file published in the GitHub repository AssemblyAI/blurt (5 stars, last pushed 4d ago), licensed MIT. It adds 22,629 tokens to every session, about $0.1131 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 2026-08-31.

Related

Other instructions, from other repositories

Applite CLAUDE.md

Instructions for milanvarady/Applite, covering claude.md, project overview, build & run, architecture and data flow.

milanvarady/Applite · 2,572 tokens

os-clovy AGENTS.md

Instructions for open-software-network/os-clovy, covering clovy — agent instructions, project, os platform (shared brain), structure and domain & decisions — read before writing code.

open-software-network/os-clovy · 4,092 tokens

scarf AGENTS.md

Instructions for awizemann/scarf: This repo carries its own agent memory — plain files in git, served by the in-repo memophant-mcp MCP server, managed by the Memophant macOS app. It works the same for every agent (Claude Code, Codex, Cursor, Gemini, Copilot). This block is regenerated between the memophant markers…

awizemann/scarf · 1,629 tokens

scarf copilot-instructions.md

Instructions for awizemann/scarf: File memory notes under one of six folders (architecture/conventions/decisions/operations/project/roadmap), never the root. When a note is grounded in code, pass sourcepaths (the repo files it depends on) so Memory Health can drift-check it — an unanchored code note can't be kept…

awizemann/scarf · 461 tokens

SkillDeck CLAUDE.md

Instructions for crossoverJie/SkillDeck, covering claude.md, code style: comments required, build & run commands, architecture and key data patterns.

crossoverJie/SkillDeck · 1,986 tokens

mectrics AGENTS.md

Instructions for farukkamcici/mectrics, covering agents.md — working agreement for mectrics, 0. golden rule: english-only repository, 1. project shape, 2. internationalization (i18n) and 3. menu bar rendering rules.

farukkamcici/mectrics · 4,487 tokens