Borrowing it
Nothing to install: this file belongs to SwiftedMind/monocle. 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/SwiftedMind/monocle/main/AGENTS.mdgit clone --depth 1 https://github.com/SwiftedMind/monocleWrote 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/swiftedmind/monocle/agents-md)<a href="https://agentmods.dev/instructions/swiftedmind/monocle/agents-md"><img src="https://agentmods.dev/badge/instructions/swiftedmind/monocle/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/swiftedmind/monocle/agents-md"><img src="https://agentmods.dev/badge/instructions/swiftedmind/monocle/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 | $0.00787 | $0.00787 |
| Opus 5.5 | $0.00315 | $0.00315 |
| Sonnet 5.5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
monocle 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Architecture & Contribution Guide
monocle is a read-only Swift code inspection tool built on top of SourceKit-LSP.
Its primary purpose is to provide a command-line equivalent of “cmd-click” in an IDE: given a file, line, and column, it resolves the symbol there and returns information about its definition and documentation.
This document gives a high-level view of how the project is structured and how it is intended to evolve, so that contributors can extend it without breaking the overall design.
General Instructions
Pay attention to these general instructions and closely follow them!
- Always prefer readability over conciseness/compactness.
- Never commit unless instructed to do so.
When you are done
- Always build the project to check for compilation errors.
- When you have added or modified Swift files, always run
swiftformat --config ".swiftformat" {files}.
Build Instructions
- Build from the repository root with
swift build. - Prefer
swift build --quietto reduce noise; only drop--quietwhen debugging a failure.
1. Purpose and Scope
- Inspect Swift symbols at a given file/line/column.
- Resolve definitions across the workspace, including packages and dependencies.
- Surface signatures and documentation via SourceKit-LSP.
- Operate in a read-only manner: no edits, no refactorings, no code generation.
The tool focuses on understanding existing Swift code, not modifying it.
2. High-Level Architecture
The project is structured into clear layers to keep responsibilities separate while allowing the daemon/server to build on the same foundations.
2.1 Core Layer
The core layer encapsulates all interaction with SourceKit-LSP and the workspace:
- Manages the lifecycle of an LSP session (starting and shutting down
sourcekit-lsp). - Sends LSP requests (e.g. “go to definition”, “hover”) and parses responses.
- Resolves the workspace (SwiftPM or Xcode) from file paths or an explicit root.
- Provides a small, stable API for “inspect the symbol at this location”.
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.
- 1mo ago First seen · 82 lines · 787 tokens per session scan A fe737ce95115
monocle AGENTS.md is an instructions file published in the GitHub repository SwiftedMind/monocle (51 stars, last pushed 9mo ago), licensed MIT. It adds 787 tokens to every session, about $0.0031 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 2026-08-30.
Other instructions, from other repositories
team-foundry copilot-instructions.md
Root instruction pointer for GitHub Copilot.
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).