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.
npx agentmods add instructions/desquared/agents-rules-skills/agents-mdgit clone --depth 1 https://github.com/Desquared/agents-rules-skillsWrote 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/desquared/agents-rules-skills/agents-md)<a href="https://agentmods.dev/instructions/desquared/agents-rules-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/desquared/agents-rules-skills/agents-md.svg" alt="Measured on agentmods" 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 | $0.01445 | $0.01445 |
| Opus 5 | $0.00723 | $0.00723 |
| Sonnet 5 | $0.00289 | $0.00289 |
| Haiku 4.5 | $0.00145 | $0.00145 |
Grade A, and why
agents-rules-skills AGENTS.md scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/Desquared/agents-rules-skills/main/agents/ios-security-reviewer.md \ How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents Catalog
Agents are role-based Markdown files. Claude Code has first-class support for sub-agents today. Cursor, Windsurf, and GitHub Copilot handle agents differently — see the per-tool notes below.
Quick Install
The interactive installer handles all IDE paths for you:
npx github:Desquared/agents-rules-skills install-agents
Pick your IDE(s), choose a scope (project or global), filter by platform, and the installer places files in the correct location — native agents folder for Claude Code, custom instructions for others.
Manual Install
How To Install An Agent
Claude Code
Claude Code loads agents from ~/.claude/agents/ (global) or .claude/agents/ (project-local). Each Markdown file becomes a sub-agent that Claude can automatically delegate to.
# Global (available in every project)
mkdir -p ~/.claude/agents
curl -fsSL https://raw.githubusercontent.com/Desquared/agents-rules-skills/main/agents/ios-security-reviewer.md \
-o ~/.claude/agents/ios-security-reviewer.md
# Project-local (only available in this project)
mkdir -p .claude/agents
curl -fsSL https://raw.githubusercontent.com/Desquared/agents-rules-skills/main/agents/ios-security-reviewer.md \
-o .claude/agents/ios-security-reviewer.md
GitHub Copilot
GitHub Copilot supports project and global agent folders.
# Global (available in every project)
mkdir -p ~/.copilot/agents
curl -fsSL https://raw.githubusercontent.com/Desquared/agents-rules-skills/main/agents/ios-security-reviewer.md \
-o ~/.copilot/agents/ios-security-reviewer.md
# Project-local (only available in this project)
mkdir -p .github/agents
curl -fsSL https://raw.githubusercontent.com/Desquared/agents-rules-skills/main/agents/ios-security-reviewer.md \
-o .github/agents/ios-security-reviewer.md
Cursor, Windsurf
These tools do not currently support a "drop a file = new sub-agent" pattern equivalent to Claude Code agents. Instead:
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.
- 4d ago First seen · 98 lines · 1,445 tokens per session scan A f2f24ec3624b
agents-rules-skills AGENTS.md is an instructions file published in the GitHub repository Desquared/agents-rules-skills (4 stars, last pushed 20d ago), licensed MIT. It adds 1,445 tokens to every session, about $0.0072 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.