agentmods.dev

shob AGENTS.md

Repository instructions for an Electron desktop application built from several Bun packages managed in one monorepo. They explain the project structure, required documents, and common commands for installing, running, checking, and building it.

In plain words
What is it for?
Use them when installing dependencies, starting the desktop app, running type checks or linting, building the embedded server, or changing this repository.
Why use it?
They give a coding agent the project context and working rules before it changes code. This reduces mistakes caused by missing architecture details or using the wrong commands.

Instructions file for CodexOpenCode

582 10d ago A scan 3,531 tokens original MIT
View the source file shobcoder/shob
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/shobcoder/shob/agents-md
Clone the repo
git clone --depth 1 https://github.com/shobcoder/shob

Made for: Codex, OpenCode.

Per session 3,531 This file is loaded in full into every session.
When invoked 3,531 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 $0.03531 $0.03531
Opus 5 $0.01766 $0.01766
Sonnet 5 $0.00706 $0.00706
Haiku 4.5 $0.00353 $0.00353

Measured yesterday against content hash 84e100d00209, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shob 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 yesterday.

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 · 324 lines

How it starts

The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for working in this repository. Read docs/ (especially docs/README.md, docs/architecture.md, docs/build-flow.md, docs/package-dependencies.md, docs/architecture-overview.md, and docs/ui-path-introduction.md) for the full picture; this file distills the rules agents must follow.

Project context

  • This repo is a desktop-only build. The CLI, TUI, and cloud/SST infra have been removed. The only way to run shob is the Electron desktop app, which embeds the shob server and renders the @shob/app SolidJS web app.
  • It is a Bun + Turborepo monorepo. Dependencies are wired as workspace:*.
  • bun install runs native build scripts (tree-sitter-*, node-pty) that need Python. If Python is unavailable, use bun install --ignore-scripts (the desktop build bundles the server dist and does not need those bindings).

Common commands

  • bun install — install all workspace packages.
  • bun run dev:desktop — run the Electron app (electron-vite dev). The predev hook builds the embedded server to packages/shob/dist/node/node.js via virtual:shob-server.
  • bun run typecheck — bun turbo typecheck across packages.
  • bun run lint — oxlint at the repo root.

Build / generate

  • To regenerate the legacy JavaScript SDK, run ./packages/sdk/js/script/build.ts.
  • After changing the public Protocol or Server HttpApi, run bun run generate from packages/client. Do not edit src/generated or src/generated-effect directly. The @shob/sdk V2 client/types under packages/sdk/js/src/v2/gen/** are also generated — never edit them by hand.
  • The embedded server is built by packages/shob/script/build-node.ts (Bun.build, target: "node", entry src/node.ts) into packages/shob/dist/node/node.js. The desktop main process loads it through the virtual:shob-server module (declared in electron.vite.config.ts).

Branch & base

  • The default branch is dev.
  • Local main ref may not exist; use dev or origin/dev for diffs.

Read the full file on GitHub · 324 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. yesterday First seen · 324 lines · 3,531 tokens per session scan A 84e100d00209

Subscribe to this mod's changes

shob AGENTS.md is an instructions file published in the GitHub repository shobcoder/shob (582 stars, last pushed 10d ago), licensed MIT. It adds 3,531 tokens to every session, about $0.0177 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.

Git and workflowai-agentsanthropicclaude-codeclicodexopencode
Related

Other instructions, from other repositories

plannotator AGENTS.md

Instructions for backnotprop/plannotator, covering plannotator, project structure, server runtimes, installation and environment variables.

backnotprop/plannotator · 30,651 tokens

solo AGENTS.md

Instructions for solo-agent/solo, covering project testing rules and project service lifecycle rules.

solo-agent/solo · 306 tokens

superset AGENTS.md

AGENTS.md instructions for superset-sh/superset, covering superset monorepo, project structure, exception: shadcn/ui components, database and releases.

superset-sh/superset · 2,316 tokens

untether GEMINI.md

Instructions for littlebearapps/untether, covering untether — gemini instructions, stack & conventions, architecture, key rules and testing.

littlebearapps/untether · 500 tokens

agent-tools AGENTS.md

Instructions for kairyou/agent-tools, covering agent instructions, build and test, layout, settled decisions and docs.

kairyou/agent-tools · 564 tokens

awesome-copilot-id AGENTS.md

Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.

GulajavaMinistudio/awesome-copilot-id · 7,686 tokens