tools-and-agent Cursor ruleA

tools-and-agent from shelra/shelracode is a Cursor rule: instructions the Cursor agent follows in that repo.

Install it, pinned
mdr add shelra/shelracode/.cursor/rules/tools-and-agent.mdc@git:20260919.db3e167

Pins git:20260919.db3e167 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
Cursor rule
Repository
shelra/shelracode
Path
.cursor/rules/tools-and-agent.mdc
Versions recorded
2
Latest version
git:20260919.db3e167, committed Sep 19, 2026
First version recorded
Sep 13, 2026
Size
2,763 bytes
Repository stars
3
License
a license file GitHub does not identify

Guidelines for the agent system and tool implementations.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Agent & Tools System

## Agent

`Agent` (`src/agent/agent.ts`) is the core orchestrator. It owns:

- A provider-neutral `ProviderAdapter` (OpenRouter cloud by default, or the
  explicit managed local llama.cpp mode). **No AI-SDK / vendor object leaves the
  agent boundary** — enforced by `src/providers/architecture.test.ts`.
- The tool set built by `createTools` (`src/toolset/tools.ts`) plus MCP tools from
  `buildMcpToolSet` (`src/mcp/runtime.ts`).
- Conversation state, context compaction (`src/agent/compaction.ts`), bounded
  repository context (`src/context/compiler.ts`), sub-agent delegation.
- Abort/cancellation and an observer contract that yields `StreamChunk` events
  to the UI / headless output.

### Agent loop

`processMessage` (async generator) streams model output, executes tool calls
via the AI SDK tool runner (bounded by `maxToolRounds`), appends results, and
repeats until no tool calls remain. Observer callbacks
(`onStepStart/onStepFinish/onToolStart/onToolFinish`) drive UI updates.

## Tool interface

AI SDK tools are declared with `tool({ description, inputSchema: z.object(...),
execute })` in `src/toolset/tools.ts`. Internal executors return a `ToolResult`
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add shelra/shelracode/.cursor/rules/tools-and-agent.mdc@sha256:f9aedd2f3d4b0b1c

The line at the top of this page pins the label git:20260919.db3e167, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_wbhrsgtizaxxo7ic.svg)](https://markdownregistry.com/a/art_wbhrsgtizaxxo7ic)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Sep 13, 2026 and Sep 19, 2026, about one every 6 days.

versioncommittedcommitsizeaudit
git:20260919.db3e167 latest2026-09-19 db3e167 2,763 BA view · diff
git:20260913.3f8e1222026-09-13 3f8e122 2,819 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (2763 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

shelra/shelracode · 3 stars · license a license file GitHub does not identify · pushed 2026-10-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_wbhrsgtizaxxo7ic
GET https://markdownregistry.com/api/v1/resolve?ref=shelra/shelracode/.cursor/rules/tools-and-agent.mdc
GET https://markdownregistry.com/api/v1/blob/f9aedd2f3d4b0b1c10d21d18dd73449d9c52730bb1e55323a4177af9e1daf539

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: Cursor rules vs AGENTS.md · which agent file does what.

More from shelra/shelracode

agent-browser SKILL.md skill
shelra/shelracode · .agents/skills/agent-browser/SKILL.md · Use the host-side `agent-browser` CLI for local browser smoke tests, screenshots, snapshots, and simple UI validation…
git:20260919.db3e167 · audit B · 3 stars
agent-desktop SKILL.md skill
shelra/shelracode · .agents/skills/agent-desktop/SKILL.md · Use the built-in `Computer` sub-agent with `agent-desktop` for macOS desktop automation. Apply when a task needs…
git:20260919.db3e167 · audit A · 3 stars
agent-memory-systems SKILL.md skill
shelra/shelracode · .agents/skills/agent-memory-systems/SKILL.md · "Memory is the cornerstone of intelligent agents. Without it, every
git:20260925.7d398e3 · audit A · 3 stars
code-review SKILL.md skill
shelra/shelracode · .agents/skills/code-review/SKILL.md · Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code…
git:20260919.7780667 · audit A · 3 stars
find-skills SKILL.md skill
shelra/shelracode · .agents/skills/find-skills/SKILL.md · Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is…
git:20260913.3f8e122 · audit A · 3 stars
impeccable SKILL.md skill
shelra/shelracode · .agents/skills/impeccable/SKILL.md · Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt…
v4.3.1 · audit A · 3 stars
shelra-workspace-quality SKILL.md skill
shelra/shelracode · .agents/skills/shelra-workspace-quality/SKILL.md · Audit or refine ShelraCode's main OpenTUI coding workspace when chat activity, live status, plan/context sidebar, agent…
git:20260913.3f8e122 · audit A · 3 stars
spec-driven-development SKILL.md skill
shelra/shelracode · .agents/skills/spec-driven-development/SKILL.md · Creates specs before coding. Use when starting a new project, feature, or significant change and no specification…
git:20260925.7d398e3 · audit A · 3 stars
AGENTS.md@.agents/skills/terminal-ui AGENTS.md file
shelra/shelracode · .agents/skills/terminal-ui/AGENTS.md
git:20260919.7780667 · audit A · 3 stars
terminal-ui SKILL.md skill
shelra/shelracode · .agents/skills/terminal-ui/SKILL.md · Terminal User Interface (TUI) performance and UX guidelines for TypeScript applications using Ink and Clack. This skill…
git:20260919.7780667 · audit A · 3 stars
development-workflow Cursor rule
shelra/shelracode · .cursor/rules/development-workflow.mdc · Development workflow and common commands
git:20260919.db3e167 · audit A · 3 stars
project-overview Cursor rule
shelra/shelracode · .cursor/rules/project-overview.mdc · Project overview and architecture reference
git:20260919.db3e167 · audit A · 3 stars

Every file in shelra/shelracode

Browse by kind, by grade A, or by owner.