agentmods.dev

embedist AGENTS.md

Project-specific instructions for working on Embedist, a Windows desktop application built with Tauri, React, TypeScript, and Rust. They document the real entry points, available commands, and how the project is actually tested.

In plain words
What is it for?
Use them to build and run Embedist, check Rust code with Clippy, create release builds, trace application entry points, and validate changes manually when no automated test suite is present.
Why use it?
They prevent an agent from relying on outdated documentation or running commands that do not exist. They also provide a quick map of where the frontend, backend, and Tauri commands live.

Instructions file for CodexOpenCode

47 3mo ago A scan 688 tokens original MIT
View the source file mandarwagh9/embedist
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/mandarwagh9/embedist/agents-md
Clone the repo
git clone --depth 1 https://github.com/mandarwagh9/embedist

Made for: Codex, OpenCode.

Per session 688 This file is loaded in full into every session.
When invoked 688 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 $0.00688 $0.00688
Opus 5 $0.00344 $0.00344
Sonnet 5 $0.00138 $0.00138
Haiku 4.5 $0.00069 $0.00069

Measured 2d ago against content hash 3bc9df49d3be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

embedist 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 · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Embedist Agent Notes

Use this file as a high-signal quick ramp for this repo.

Scope and source of truth

  • Work in embedist/embedist (the parent folder embedist/ is not the app root).
  • Trust executable config over docs when they differ (README version text can lag).
  • Platform target is Windows desktop (Tauri 2 + React + TypeScript + Rust).

Commands that actually exist

  • Root frontend scripts (package.json): npm run dev, npm run build, npm run preview, npm run tauri.
  • There is no root npm run lint or npm test script.
  • Fast local verification:
    • npm run build
    • cargo clippy --manifest-path src-tauri/Cargo.toml
  • Run app in dev: npm run tauri dev
  • Build release artifacts: npm run tauri build

Testing reality

  • No automated test suite is present (*.test.*, *.spec.*, and src-tauri/tests are absent).
  • Validation is build + clippy + manual app checks.

Architecture map (real entrypoints)

  • Frontend entry: src/main.tsx -> src/App.tsx.
  • Backend entry: src-tauri/src/main.rs -> src-tauri/src/lib.rs.
  • Tauri commands are registered in src-tauri/src/lib.rs and implemented in src-tauri/src/commands/*.rs.
  • Prompt system is file-based: src/lib/prompts/modes/*.md loaded via src/lib/prompts/index.ts.

AI/tool-calling facts that matter

  • Rust backend supports tool-enabled chat handlers for OpenAI, Anthropic, DeepSeek, and custom OpenAI-compatible endpoints (src-tauri/src/commands/ai.rs).
  • Ollama and Google handlers are text/chat only in current backend implementation.
  • Agent-mode tool execution is implemented in src/hooks/useAgent.ts + src/lib/agent-tools.ts.

Rust and state gotchas

  • For cloneable async shared process state, use Arc<tokio::sync::Mutex<...>> (see BuildState in src-tauri/src/commands/platformio.rs).
  • Avoid Option::is_none_or(...); use stable alternatives like is_some_and(...).
  • run_shell in src-tauri/src/commands/filesystem.rs rejects shell metacharacters; do not expect complex chained shell expressions through that command.

Read the full file on GitHub · 59 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 · 59 lines · 688 tokens per session scan A 3bc9df49d3be

Subscribe to this mod's changes

embedist AGENTS.md is an instructions file published in the GitHub repository mandarwagh9/embedist (47 stars, last pushed 3mo ago), licensed MIT. It adds 688 tokens to every session, about $0.0034 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.

aiai-agentsdeveloper-toolsembeddedembedded-softwareembedded-systems
Related

Other instructions, from other repositories

kernel_chat GEMINI.md

Instructions for Ravi-Teja-konda/kernel_chat, covering building and running, writing tests, test structure and framework, mocking (vi from vitest) and commonly mocked modules.

Ravi-Teja-konda/kernel_chat · 3,711 tokens

FastLED CLAUDE.md

Claude Code instructions for FastLED/FastLED, covering fastled ai agent guidelines, read the right file for your task, key commands, core rules (all agents) and git and code publishing.

FastLED/FastLED · 2,927 tokens

memvid CLAUDE.md

Claude Code instructions for memvid/memvid, covering claude.md, project overview, architecture, core components and file format (.mv2).

memvid/memvid · 736 tokens

monkey AGENTS.md

Instructions for monkey/monkey, covering agents, repository map, main runtime flow, build and verification and commit style used in this repository.

monkey/monkey · 1,431 tokens

p3a CLAUDE.md

Claude Code instructions for fabkury/p3a, covering claude.md, project overview, build management, build commands and set pythonutf8 to avoid unicode encoding errors on windows.

fabkury/p3a · 1,698 tokens

Serial-Studio CLAUDE.md

Claude Code instructions for Serial-Studio/Serial-Studio, covering claude.md, behavioral rules, context canary — last line of every response, trust contract and scripts.

Serial-Studio/Serial-Studio · 7,251 tokens